A triangulation-based technique for building boundary identification from point cloud data
- Authors: Awrangjeb, Mohammad , Lu, Guojun
- Date: 2016
- Type: Text , Conference proceedings , Conference paper
- Relation: 2015 International Conference on Image and Vision Computing New Zealand, IVCNZ 2015; Auckland, New Zealand; 23rd-24th November 2015 Vol. 2016-November, p. 1-6
- Full Text: false
- Reviewed:
- Description: Building boundary identification is an essential prerequisite in building outline generation from point cloud data. In this problem, boundary edges that constitute the building boundary are identified. The existing solutions to the identification of boundary edges from the input point set have one or more of the following problems: ineffective in finding appropriate edges in a concave shape, incapable of determining a 'hole' or 'concavity' inside the shape separately, dependant on additional information such as the scan direction that may be unavailable, and incompetent in determining the boundary of a point set from the boundaries of two or more subsets of the point set. This paper proposes a new solution to the identification of building boundary by using the maximum point-to-point distance in the input data. It properly detects the boundary edges for any type of shape and separately recognises holes, if any, inside the shape. The unique feature of the proposed solution is that it can identify the boundary of a point set from the boundaries of two or more subsets of the point set. It does not require any additional information other than the input point set. Experimental results show that the proposed solution can preserve details along the building boundary and offer high area-based completeness and quality, even in low density input data. © 2015 IEEE.
- Description: International Conference Image and Vision Computing New Zealand
Achieving high multi-modal registration performance using simplified Hough-transform with improved symmetric-SIFT
- Authors: Hossain, Md Tanvir , Teng, Shyh , Lu, Guojun
- Date: 2012
- Type: Text , Conference paper
- Relation: 14th International Conference on Digital Image Computing Techniques and Applications, DICTA 2012
- Full Text: false
- Reviewed:
- Description: The traditional way of using Hough Transform with SIFT is for the purpose of reliable object recognition. However, it cannot be effectively applied to image registration in the same way as the recall rate can be significantly lower. In this paper, we propose an alternative implementation of Hough Transform that can be used with Improved Symmetric-SIFT for multi-modal image registration. Our experimental results show that the proposed technique of applying Hough Transform can significantly improve the key-point matching as well as registration accuracy by utilizing aggregated information from key-points throughout the input images.
Adversarial network with multiple classifiers for open set domain adaptation
- Authors: Shermin, Tasfia , Lu, Guojun , Teng, Shyh , Murshed, Manzur , Sohel, Ferdous
- Date: 2021
- Type: Text , Journal article
- Relation: IEEE Transactions on Multimedia Vol. 23, no. (2021), p. 2732-2744
- Full Text:
- Reviewed:
- Description: Domain adaptation aims to transfer knowledge from a domain with adequate labeled samples to a domain with scarce labeled samples. Prior research has introduced various open set domain adaptation settings in the literature to extend the applications of domain adaptation methods in real-world scenarios. This paper focuses on the type of open set domain adaptation setting where the target domain has both private ('unknown classes') label space and the shared ('known classes') label space. However, the source domain only has the 'known classes' label space. Prevalent distribution-matching domain adaptation methods are inadequate in such a setting that demands adaptation from a smaller source domain to a larger and diverse target domain with more classes. For addressing this specific open set domain adaptation setting, prior research introduces a domain adversarial model that uses a fixed threshold for distinguishing known from unknown target samples and lacks at handling negative transfers. We extend their adversarial model and propose a novel adversarial domain adaptation model with multiple auxiliary classifiers. The proposed multi-classifier structure introduces a weighting module that evaluates distinctive domain characteristics for assigning the target samples with weights which are more representative to whether they are likely to belong to the known and unknown classes to encourage positive transfers during adversarial training and simultaneously reduces the domain gap between the shared classes of the source and target domains. A thorough experimental investigation shows that our proposed method outperforms existing domain adaptation methods on a number of domain adaptation datasets. © 1999-2012 IEEE.
An Attention-Based Approach for Single Image Super Resolution
- Authors: Liu, Yuan , Wang, Yuancheng , Li, Nan , Cheng, Xu , Zhang, Yifeng , Huang, Yongming , Lu, Guojun
- Date: 2018
- Type: Text , Conference proceedings , Conference paper
- Relation: 2018 24th International Conference on Pattern Recognition, ICPR 2018; Beijing, China; 20th-24th August 2018 Vol. 2018, p. 2777-2784
- Full Text:
- Reviewed:
- Description: The main challenge of single image super resolution (SISR) is the recovery of high frequency details such as tiny textures. However, most of the state-of-the-art methods lack specific modules to identify high frequency areas, causing the output image to be blurred. We propose an attention-based approach to give a discrimination between texture areas and smooth areas. After the positions of high frequency details are located, high frequency compensation is carried out. This approach can incorporate with previously proposed SISR networks. By providing high frequency enhancement, better performance and visual effect are achieved. We also propose our own SISR network composed of DenseRes blocks. The block provides an effective way to combine the low level features and high level features. Extensive benchmark evaluation shows that our proposed method achieves significant improvement over the state-of-the-art works in SISR.
An automatic building extraction and regularisation technique using LiDAR point cloud data and orthoimage
- Authors: Gilani, Sayed Ali Naqi , Awrangjeb, Mohammad , Lu, Guojun
- Date: 2016
- Type: Text , Journal article
- Relation: Remote Sensing Vol. 8, no. 3 (2016), p. 1-27
- Full Text:
- Reviewed:
- Description: The development of robust and accurate methods for automatic building detection and regularisation using multisource data continues to be a challenge due to point cloud sparsity, high spectral variability, urban objects differences, surrounding complexity, and data misalignment. To address these challenges, constraints on object's size, height, area, and orientation are generally benefited which adversely affect the detection performance. Often the buildings either small in size, under shadows or partly occluded are ousted during elimination of superfluous objects. To overcome the limitations, a methodology is developed to extract and regularise the buildings using features from point cloud and orthoimagery. The building delineation process is carried out by identifying the candidate building regions and segmenting them into grids. Vegetation elimination, building detection and extraction of their partially occluded parts are achieved by synthesising the point cloud and image data. Finally, the detected buildings are regularised by exploiting the image lines in the building regularisation process. Detection and regularisation processes have been evaluated using the ISPRS benchmark and four Australian data sets which differ in point density (1 to 29 points/m2), building sizes, shadows, terrain, and vegetation. Results indicate that there is 83% to 93% per-area completeness with the correctness of above 95%, demonstrating the robustness of the approach. The absence of over- and many-to-many segmentation errors in the ISPRS data set indicate that the technique has higher per-object accuracy. While compared with six existing similar methods, the proposed detection and regularisation approach performs significantly better on more complex data sets (Australian) in contrast to the ISPRS benchmark, where it does better or equal to the counterparts. © 2016 by the authors.
An effective and efficient contour-based corner detector using simple triangular theory
- Authors: Sadat, Rafi , Teng, Shyh , Lu, Guojun
- Date: 2011
- Type: Text , Conference paper
- Relation: 19th Pacific Conference on Computer Graphics and Applications p. 37-42
- Full Text: false
- Reviewed:
- Description: Corner detection is an important operation in many computer vision applications. Among the contour-based corner detectors in the literature, the Chord-to-Point Distance Accumulation (CPDA) detector is reported to have one of the best repeatability and lowest localization error. However, we found that CPDA detector often fails to accurately detect the true corners in some situations. Furthermore, CPDA detector is also computationally expensive. To overcome these weaknesses of CPDA detector, we propose an effective but yet efficient corner detector using a simple triangular theory. Our experimental results show that our proposed detector outperforms CPDA and six other existing detectors in terms of repeatability. Our proposed detector also has one of the lowest localization error. Finally it is computationally the most efficient.
An effective method of estimating scale-invariant interest region for representing corner features
- Authors: Sadat, Rafi , Teng, Shyh , Lu, Guojun
- Date: 2012
- Type: Text , Conference paper
- Relation: 27th Conference on Image and Vision Computing New Zealand p. 73-78
- Full Text: false
- Reviewed:
- Description: To achieve scale-invariance, the approach used by many corner detection and description methods is to derive an appropriate scale as part of the process of detecting each corner and then use this scale for estimating region(s) around the corner to build the descriptor(s). However, this approach is not suitable for methods that do not derive such scale information in their corner detection process. This paper proposes a new method for selecting regions around a corner so that descriptors, which are invariant to scale changes and other image transformations, can be built to represent the corner. Our experimental results show that our proposed method achieves better precision-and-recall results than existing methods.
An enhancement to closed-form method for natural image matting
- Authors: Zhu, Jun , Zhang, Dengsheng , Lu, Guojun
- Date: 2010
- Type: Text , Conference paper
- Relation: Proceedings of the 2010 Digital Image Computing: Techniques and Applications p. 629-634
- Full Text: false
- Reviewed:
- Description: Natural image matting is a task to estimate fractional opacity of foreground layer from an image. Many matting methods have been proposed, and most of them are trimap-based. Among these methods, closed-form matting offers both trimap-based and scribble-based matting. However, the closed-form method causes significant errors at background-hole regions due to over-smoothing. In this paper, we identify the source of the problem and propose our solution to enhance the closed-form method. Experiments show that our enhanced method can improve the accuracy for trimap-based images and obtain similar result to the closed-form method for scribble-based matting.
An enhancement to SIFT-based techniques for image registration
- Authors: Hossain, Tanvir , Teng, Shyh , Lu, Guojun , Lackmann, Martin
- Date: 2010
- Type: Text , Conference paper
- Relation: Proceedings of the 2010 Digital Image Computing: Techniques and Applications p. 166-171
- Full Text: false
- Reviewed:
- Description: Symmetric-SIFT is a recently proposed local technique used for registering multimodal images. It is based on a well-known general image registration technique named Scale Invariant Feature Transform (SIFT). Symmetric SIFT makes use of the gradient magnitude information at the image's key regions to build the descriptors. In this paper, we highlight an issue with how the magnitude information is used in this process. This issue may result in similar descriptors being built to represent regions in images that are visually different. To address this issue, we have proposed two new strategies for weighting the descriptors. Our experimental results show that Symmetric-SIFT descriptors built using our proposed strategies can lead to better registration accuracy than descriptors built using the original Symmetric-SIFT technique. The issue highlighted and the two strategies proposed are also applicable to the general SIFT technique.
An enhancement to the spatial pyramid matching for image classification and retrieval
- Authors: Karmakar, Priyabrata , Teng, Shyh , Lu, Guojun , Zhang, Dengsheng
- Date: 2020
- Type: Text , Journal article
- Relation: IEEE Access Vol. 8, no. (2020), p. 22463-22472
- Full Text:
- Reviewed:
- Description: Spatial pyramid matching (SPM) is one of the widely used methods to incorporate spatial information into the image representation. Despite its effectiveness, the traditional SPM is not rotation invariant. A rotation invariant SPM has been proposed in the literature but it has many limitations regarding the effectiveness. In this paper, we investigate how to make SPM robust to rotation by addressing those limitations. In an SPM framework, an image is divided into an increasing number of partitions at different pyramid levels. In this paper, our main focus is on how to partition images in such a way that the resulting structure can deal with image-level rotations. To do that, we investigate three concentric ring partitioning schemes. Apart from image partitioning, another important component of the SPM framework is a weight function. To apportion the contribution of each pyramid level to the final matching between two images, the weight function is needed. In this paper, we propose a new weight function which is suitable for the rotation-invariant SPM structure. Experiments based on image classification and retrieval are performed on five image databases. The detailed result analysis shows that we are successful in enhancing the effectiveness of SPM for image classification and retrieval. © 2013 IEEE.
An improved building detection in complex sites using the LIDAR height variation and point density
- Authors: Siddiqui, Fasahat , Teng, Shyh , Lu, Guojun , Awrangjeb, Mohammad
- Date: 2013
- Type: Text , Conference proceedings
- Relation: 2013 28th International Conference on Image and Vision Computing New Zealand, IVCNZ 2013; Wellington; New Zealand; 27th-29th November 2013; published in International Conference Image and Vision Computing New Zealand p. 471-476
- Full Text:
- Reviewed:
- Description: In this paper, the height variation in LIDAR (Light Detection And Ranging) point cloud data and point density are analyzed to remove the false building detection in highly vegetation and hilly sites. In general, the LIDAR points in a tree area have higher height variations than those in a building area. Moreover, the density of points having similar height values is lower in a tree area than in a building area. The proposed method uses such information as an improvement to a current state-of-the-art building detection method. The qualitative and object-based quantitative analyzes have been performed to verify the effectiveness of the proposed building detection method as compared with a current method. The analysis shows that proposed building detection method successfully reduces false building detection (i.e. trees in high complex sites of Australia and Germany), and the average correctness and quality have been improved by 6.36% and 6.16% respectively.
An improved curvature scale-space corner detector and a robust corner matching approach for transformed image identification
- Authors: Awrangjeb, Mohammad , Lu, Guojun
- Date: 2008
- Type: Text , Journal article
- Relation: Image Processing, IEEE Transactions Vol. 17, no. 12 (2008), p. 2425-2441
- Full Text: false
- Reviewed:
- Description: There are many applications, such as image copyright protection, where transformed images of a given test image need to be identified. The solution to this identification problem consists of two main stages. In stage one, certain representative features, such as corners, are detected in all images. In stage two, the representative features of the test image and the stored images are compared to identify the transformed images for the test image. Curvature scale-space (CSS) corner detectors look for curvature maxima or inflection points on planar curves. However, the arc-length used to parameterize the planar curves by the existing CSS detectors is not invariant to geometric transformations such as scaling. As a solution to stage one, this paper presents an improved CSS corner detector using the affine-length parameterization which is relatively invariant to affine transformations. We then present an improved corner matching technique as a solution to the stage two. Finally, we apply the proposed corner detection and matching techniques to identify the transformed images for a given image and report the promising results.
Anti-aliasing deep image classifiers using novel depth adaptive blurring and activation function
- Authors: Hossain, Md Tahmid , Teng, Shyh , Lu, Guojun , Rahman, Mohammad Arifur , Sohel, Ferdous
- Date: 2023
- Type: Text , Journal article
- Relation: Neurocomputing Vol. 536, no. (2023), p. 164-174
- Full Text: false
- Reviewed:
- Description: Deep convolutional networks are vulnerable to image translation or shift, partly due to common down-sampling layers, e.g., max-pooling and strided convolution. These operations violate the Nyquist sampling rate and cause aliasing. The textbook solution is low-pass filtering (blurring) before down-sampling, which can benefit deep networks as well. Even so, non-linearity units, such as ReLU, often re-introduce the problem, suggesting that blurring alone may not suffice. In this work, first, we analyse deep features with Fourier transform and show that Depth Adaptive Blurring is more effective, as opposed to monotonic blurring. To this end, we propose a novel Depth Adaptive Blur-pool (DAB-pool) module to replace existing down-sampling methods. Second, we introduce a novel activation function – with a built-in low pass filter, as an additional measure, to keep the problem from reappearing. From experiments, we observe generalisation on other forms of transformations and corruptions as well, e.g., rotation, scale, and noise. We evaluate our method under three challenging settings: (1) a variety of image translations; (2) adversarial attacks – both
Automatic building extraction from LIDAR data covering complex urban scenes
- Authors: Awrangjeb, Mohammad , Lu, Guojun , Fraser, Clive
- Date: 2014
- Type: Text , Conference proceedings
- Relation: ISPRS Technical Commission III Symposium; Zurich, Switzerland; 5th-7th September 2014; published in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences Vol. XL-3, p. 25-32
- Relation: http://purl.org/au-research/grants/arc/DE120101778
- Full Text:
- Reviewed:
- Description: This paper presents a new method for segmentation of LIDAR point cloud data for automatic building extraction. Using the ground height from a DEM (Digital Elevation Model), the non-ground points (mainly buildings and trees) are separated from the ground points. Points on walls are removed from the set of non-ground points by applying the following two approaches: If a plane fitted at a point and its neighbourhood is perpendicular to a fictitious horizontal plane, then this point is designated as a wall point. When LIDAR points are projected on a dense grid, points within a narrow area close to an imaginary vertical line on the wall should fall into the same grid cell. If three or more points fall into the same cell, then the intermediate points are removed as wall points. The remaining non-ground points are then divided into clusters based on height and local neighbourhood. One or more clusters are initialised based on the maximum height of the points and then each cluster is extended by applying height and neighbourhood constraints. Planar roof segments are extracted from each cluster of points following a region-growing technique. Planes are initialised using coplanar points as seed points and then grown using plane compatibility tests. If the estimated height of a point is similar to its LIDAR generated height, or if its normal distance to a plane is within a predefined limit, then the point is added to the plane. Once all the planar segments are extracted, the common points between the neghbouring planes are assigned to the appropriate planes based on the plane intersection line, locality and the angle between the normal at a common point and the corresponding plane. A rule-based procedure is applied to remove tree planes which are small in size and randomly oriented. The neighbouring planes are then merged to obtain individual building boundaries, which are regularised based on long line segments. Experimental results on ISPRS benchmark data sets show that the proposed method offers higher building detection and roof plane extraction rates than many existing methods, especially in complex urban scenes.
Automatic building footprint extraction and regularisation from LIDAR point cloud data
- Authors: Awrangjeb, Mohammad , Lu, Guojun
- Date: 2014
- Type: Text , Conference proceedings
- Full Text: false
- Description: This paper presents a segmentation of LIDAR point cloud data for automatic extraction of building footprint. Using the ground height information from a DEM (Digital Elevation Model), the non-ground points (mainly buildings and trees) are separated from the ground points. Points on walls are removed from the set of non-ground points. The remaining non-ground points are then divided into clusters based on height and local neighbourhood. Planar roof segments are extracted from each cluster of points following a region-growing technique. Planes are initialised using coplanar points as seed points and then grown using plane compatibility tests. Once all the planar segments are extracted, a rule-based procedure is applied to remove tree planes which are small in size and randomly oriented. The neighbouring planes are then merged to obtain individual building boundaries, which are regularised based on a new feature-based technique. Corners and line-segments are extracted from each boundary and adjusted using the assumption that each short building side is parallel or perpendicular to one or more neighbouring long building sides. Experimental results on five Australian data sets show that the proposed method offers higher correctness rate in building footprint extraction than a state-of-the-art method.
Automatic categorization of image regions using dominant color based vector quantization
- Authors: Islam, Md , Zhang, Dengsheng , Lu, Guojun
- Date: 2008
- Type: Text , Conference paper
- Relation: Proceedings of the Digital Image Computing: Techniques and Applications p. 191-198
- Full Text: false
- Reviewed:
- Description: This paper proposes a dominant color based vector quantization algorithm that automatically categorizes image regions. In contrast to the conventional vector quantization algorithm, the new algorithm effectively handles variable feature vectors like dominant color descriptors. Furthermore, the algorithm is guided by a novel splitting and stopping criterion which is specially designed for dominant color descriptors. This criterion helps the algorithm not only to learn the number of clusters, but also to avoid unnecessary over-fragmentations of region-clusters. Experimental result shows that the proposed approach categorizes image-regions with very high accuracy.
Automatic Extraction of Buildings in an Urban Region
- Authors: Siddiqui, Fasahat , Teng, Shyh , Lu, Guojun , Awrangjeb, Mohammad
- Date: 2014
- Type: Text , Conference proceedings
- Relation: 29th International Conference on Image and Vision Computing New Zealand, IVCNZ 2014; Hamilton; New Zealand; 19th-21st November 2014; published in ACM International Conference Proceeding Series p. 178-183
- Full Text:
- Reviewed:
- Description: There are currently several automatic building extraction methods introduced in the literature, but none of them are capable to completely extract portions of a building that are below a pre-defined building minimum height threshold. This paper proposes a systematic method which analyzes the height differences between the extracted adjacent planes above and below the height threshold as well as the planes' connectivity, thereby, extracting all portions belonging to buildings more completely. In general, the height difference between the edges of the adjacent planes above and below the height threshold that belong to the same building is more uniform. In addition, the extracted planes below the height threshold that belong to a building and their adjacent ground planes also have a clear height difference. The proposed method incorporates such information to achieve better performance in building extraction. We have compared our proposed method to a current state-of-the-art building extraction method qualitatively and quantitatively. Our experimental results show that our proposed method successfully recovers portions of a building below the height threshold, thereby achieving relatively higher average completeness (an improvement of 1.14%) and quality (an improvement of 0.93%).
Automatic segmentation of LiDAR point cloud data at different height levels for 3D building extraction C3 - Proceedings - IEEE International Conference on Multimedia and Expo
- Authors: Abdullah, S.M. , Awrangjeb, Mohammad , Lu, Guojun
- Date: 2014
- Type: Text , Conference proceedings
- Full Text: false
- Description: This paper presents a new LiDAR segmentation technique for automatic building detection and roof plane extraction. First, it uses a height threshold, based on the digital elevation model it divides the LiDAR point cloud into 'ground' and 'non-ground' points. Then, starting from the maximum LiDAR height, and decreasing the height at each iteration, it looks for points to form planar roof segments. At each height level, it clusters the points based on the distance and finds straight lines using the points. The nearest coplanar point to the midpoint of each line is used as a seed point and the plane is grown in a region growing fashion. Finally, a rule-based procedure is followed to remove planar segments in trees. The experimental results show that the proposed technique offers a high building detection and roof plane extraction rates while compared to other recently proposed techniques.
BackNet: An Enhanced backbone network for accurate detection of objects with large scale variations
- Authors: Hossain, Md Tahmid , Teng, Shyh Wei , Lu, Guojun
- Date: 2019
- Type: Text , Book chapter
- Relation: Image and Video Technology. PSIVT 2019 p. 52-64
- Full Text: false
- Reviewed:
- Description: Deep Convolutional Neural Networks (CNNs) have induced significant progress in the field of computer vision including object detection and classification. Two-stage detectors like Faster RCNN and its variants are found to be more accurate compared to its one-stage counter-parts. Faster RCNN combines an ImageNet pretrained backbone network (e.g VGG16) and a Region Proposal Network (RPN) for object detection. Although Faster RCNN performs well on medium and large scale objects, detecting smaller ones with high accuracy while maintaining stable performance on larger objects still remains a challenging task. In this work, we focus on designing a robust backbone network for Faster RCNN that is capable of detecting objects with large variations in scale. Considering the difficulties posed by small objects, our aim is to design a backbone network that allows signals extracted from small objects to be propagated right through to the deepest layers of the network. This being our motivation, we propose a robust network: BackNet, which can be integrated as a backbone into any two-stage detector. We evaluate the performance of BackNet-Faster RCNN on MS COCO dataset and show that the proposed method outperforms five contemporary methods.
Bidirectional mapping coupled GAN for generalized zero-shot learning
- Authors: Shermin, Tasfia , Teng, Shyh , Sohel, Ferdous , Murshed, Manzur , Lu, Guojun
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Transactions on Image Processing Vol. 31, no. (2022), p. 721-733
- Full Text:
- Reviewed:
- Description: Bidirectional mapping-based generalized zero-shot learning (GZSL) methods rely on the quality of synthesized features to recognize seen and unseen data. Therefore, learning a joint distribution of seen-unseen classes and preserving the distinction between seen-unseen classes is crucial for GZSL methods. However, existing methods only learn the underlying distribution of seen data, although unseen class semantics are available in the GZSL problem setting. Most methods neglect retaining seen-unseen classes distinction and use the learned distribution to recognize seen and unseen data. Consequently, they do not perform well. In this work, we utilize the available unseen class semantics alongside seen class semantics and learn joint distribution through a strong visual-semantic coupling. We propose a bidirectional mapping coupled generative adversarial network (BMCoGAN) by extending the concept of the coupled generative adversarial network into a bidirectional mapping model. We further integrate a Wasserstein generative adversarial optimization to supervise the joint distribution learning. We design a loss optimization for retaining distinctive information of seen-unseen classes in the synthesized features and reducing bias towards seen classes, which pushes synthesized seen features towards real seen features and pulls synthesized unseen features away from real seen features. We evaluate BMCoGAN on benchmark datasets and demonstrate its superior performance against contemporary methods. © 1992-2012 IEEE.