An automatic building extraction and regularisation technique using LiDAR point cloud data and orthoimage
- Gilani, Sayed Ali Naqi, Awrangjeb, Mohammad, Lu, Guojun
- 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.
- 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.
How to raise a ghost : the haunted house as a metaphor for the haunted self
- Authors: Proposch, Melissa
- Date: 2023
- Type: Text , Thesis , Masters
- Full Text:
- Description: This investigation takes an artistic autoethnographic journey in search of the haunted self. As an entangled form of research, it weaves the narrative and analytical into reciprocal relationships. Its methodology and conclusions tell a ghost story. An investigation of one’s haunted self is by nature an examination of personal ghosts and family shadows. This research documents a process of discovery, of looking for and finding my interior haunted house and the psychic home of family trauma and secrets. An examination of this tender and volatile site calls for intuitive and caring exploration and reading. Confinement during Covid-19 pandemic lockdowns further brought into focus my actual home as a site of exhumed memories. There, I developed strategies for attunement to the signs and stories of family ghosts. This process led to newly imagined narrative approaches for artmaking. The story of the haunted house is dark and curious, offering a metaphor for the negative psychological space of the family home, and embracing dystopian aesthetics. Metaphors play with meaning and draw symbolic likenesses to make their language expansive. This research explores how a visual language made for ghost story telling can draw upon the symbolic and metaphorical to express the nebulous and unsettling. It also examines the inherent spectrality of some arts technologies and their capacity to cultivate space and give voice to our phantasmagoric other. This investigation has also been informed by the practice of two artists for whom invocations of the ghostly are conceptually fundamental. Through engagement with their haunted selves, Tracey Moffatt and Louise Bourgeois provide raw access to the personal, familial, and societal shadows which haunt us all. Autoethnographers prefer to reveal meaning through process rather than declarative statements. The journey into my imaginary shadowlands culminates in the retrieval of a haunted object as artwork. Invoking the smoke and mirrors of nineteenth century spiritualism, this work embodies the notion of the artist as medium, calling upon tacit experience to bring forth image, then dialogue, and therein, the communion to be found in shared meaning. Partial fulfilment of requirements for Master of Arts
- Description: Thesis
- Authors: Proposch, Melissa
- Date: 2023
- Type: Text , Thesis , Masters
- Full Text:
- Description: This investigation takes an artistic autoethnographic journey in search of the haunted self. As an entangled form of research, it weaves the narrative and analytical into reciprocal relationships. Its methodology and conclusions tell a ghost story. An investigation of one’s haunted self is by nature an examination of personal ghosts and family shadows. This research documents a process of discovery, of looking for and finding my interior haunted house and the psychic home of family trauma and secrets. An examination of this tender and volatile site calls for intuitive and caring exploration and reading. Confinement during Covid-19 pandemic lockdowns further brought into focus my actual home as a site of exhumed memories. There, I developed strategies for attunement to the signs and stories of family ghosts. This process led to newly imagined narrative approaches for artmaking. The story of the haunted house is dark and curious, offering a metaphor for the negative psychological space of the family home, and embracing dystopian aesthetics. Metaphors play with meaning and draw symbolic likenesses to make their language expansive. This research explores how a visual language made for ghost story telling can draw upon the symbolic and metaphorical to express the nebulous and unsettling. It also examines the inherent spectrality of some arts technologies and their capacity to cultivate space and give voice to our phantasmagoric other. This investigation has also been informed by the practice of two artists for whom invocations of the ghostly are conceptually fundamental. Through engagement with their haunted selves, Tracey Moffatt and Louise Bourgeois provide raw access to the personal, familial, and societal shadows which haunt us all. Autoethnographers prefer to reveal meaning through process rather than declarative statements. The journey into my imaginary shadowlands culminates in the retrieval of a haunted object as artwork. Invoking the smoke and mirrors of nineteenth century spiritualism, this work embodies the notion of the artist as medium, calling upon tacit experience to bring forth image, then dialogue, and therein, the communion to be found in shared meaning. Partial fulfilment of requirements for Master of Arts
- Description: Thesis
Predicting neural activity of whole body cast shadow through object cast shadow in dynamic environments
- Giannopulu, Irini, Lee, Khai, Abdi, Elahe, Noori-Hoshyar, Azadeh, Brotto, Gaelle, Van Velsen, Mathew, Lin, Tiffany, Gauchan, Priya, Gorman, Jazmin, Indelicato, Giuseppa
- Authors: Giannopulu, Irini , Lee, Khai , Abdi, Elahe , Noori-Hoshyar, Azadeh , Brotto, Gaelle , Van Velsen, Mathew , Lin, Tiffany , Gauchan, Priya , Gorman, Jazmin , Indelicato, Giuseppa
- Date: 2024
- Type: Text , Journal article
- Relation: Frontiers in Psychology Vol. 15, no. (2024), p.
- Full Text:
- Reviewed:
- Description: Shadows, as all other objects that surround us, are incorporated into the body and extend the body mediating perceptual information. The current study investigates the hypothesis according to which the perception of object shadows would predict the perception of body shadows. 38 participants (19 males and 19 females) aged 23 years on average were immersed into a virtual reality environment and instructed to perceive and indicate the coincidence or non coincidence between the movement of a ball shadow with regard to ball movement on the one hand, and between their body shadow and their body position in space on the other. Their brain activity was recording via a 32-channel EEG system, in which beta (13.5–30 Hz) oscillations were analyzed. A series of Multiple Regression Analysis (MRA) revealed that the beta dynamic oscillations patterns of the bilateral occipito-parieto-frontal pathway associated with the perception of ball shadow appeared to be a significant predictor of the increase in beta oscillations across frontal areas related to the body shadow perception and the decrease in beta oscillations across frontal areas connected to the decision making of the body shadow. Taken together, the findings suggest that inferential thinking ability relative to body shadow would be reliably predicted from object shadows and that the bilateral beta oscillatory modulations would be indicative of the formation of predictive neural frontal assemblies, which encode and infer body shadow neural representation, that is, a substitution of the physical body. Copyright © 2024 Giannopulu, Lee, Abdi, Noori-Hoshyar, Brotto, Van Velsen, Lin, Gauchan, Gorman and Indelicato.
- Authors: Giannopulu, Irini , Lee, Khai , Abdi, Elahe , Noori-Hoshyar, Azadeh , Brotto, Gaelle , Van Velsen, Mathew , Lin, Tiffany , Gauchan, Priya , Gorman, Jazmin , Indelicato, Giuseppa
- Date: 2024
- Type: Text , Journal article
- Relation: Frontiers in Psychology Vol. 15, no. (2024), p.
- Full Text:
- Reviewed:
- Description: Shadows, as all other objects that surround us, are incorporated into the body and extend the body mediating perceptual information. The current study investigates the hypothesis according to which the perception of object shadows would predict the perception of body shadows. 38 participants (19 males and 19 females) aged 23 years on average were immersed into a virtual reality environment and instructed to perceive and indicate the coincidence or non coincidence between the movement of a ball shadow with regard to ball movement on the one hand, and between their body shadow and their body position in space on the other. Their brain activity was recording via a 32-channel EEG system, in which beta (13.5–30 Hz) oscillations were analyzed. A series of Multiple Regression Analysis (MRA) revealed that the beta dynamic oscillations patterns of the bilateral occipito-parieto-frontal pathway associated with the perception of ball shadow appeared to be a significant predictor of the increase in beta oscillations across frontal areas related to the body shadow perception and the decrease in beta oscillations across frontal areas connected to the decision making of the body shadow. Taken together, the findings suggest that inferential thinking ability relative to body shadow would be reliably predicted from object shadows and that the bilateral beta oscillatory modulations would be indicative of the formation of predictive neural frontal assemblies, which encode and infer body shadow neural representation, that is, a substitution of the physical body. Copyright © 2024 Giannopulu, Lee, Abdi, Noori-Hoshyar, Brotto, Van Velsen, Lin, Gauchan, Gorman and Indelicato.
- «
- ‹
- 1
- ›
- »