Faisal Z. Qureshi
Research Subjects
Faisal Z. Qureshi has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Demetri Terzopoulos
University of California Los Angeles
2 shared publications - Ken Qian Pu
University of Ontario Institute of Technology
2 shared publications - Mohamed A. Helala
University of Ontario Institute of Technology
2 shared publications - Tony Joseph
University of Ontario Institute of Technology
2 shared publications - Dhavide A. Aruliah
University of Ontario Institute of Technology
1 shared publication - Eric Ng
Faculty of Science University of Ontario Institute of Technology Canada
1 shared publication
Latest Publications
- 11 August 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 44 (2) , 905-923
A Stream Algebra for Performance Optimization of Large Scale Computer Vision Pipelines
There is a large growth in hardware and software systems capable of producing vast amounts of image and video data. These systems are rich sources of continuous image and video streams. This motivates researchers to build scalable computer vision systems that utilize data-streaming concepts for processing of visual data streams. However, several challenges exist in building large-scale computer vision systems. For example, computer vision algorithms have different accuracy and speed profiles depending on the content, type, and speed of incoming data. Also, it is not clear how to adaptively tune these algorithms in large-scale systems. These challenges exist because we lack formal frameworks for building and optimizing large-scale visual processing. This paper presents formal methods and algorithms that aim to overcome these challenges and improve building and optimizing large-scale computer vision systems. We describe a formal algebra framework for the mathematical description of computer vision pipelines for processing image and video streams. The algebra naturally describes feedback control and provides a formal and abstract method for optimizing computer vision pipelines. We then show that a general optimizer can be used with the feedback-control mechanisms of our stream algebra to provide a common online parameter optimization method for computer vision pipelines.
- 11 August 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 44 (2) , 905-923
A Stream Algebra for Performance Optimization of Large Scale Computer Vision Pipelines
There is a large growth in hardware and software systems capable of producing vast amounts of image and video data. These systems are rich sources of continuous image and video streams. This motivates researchers to build scalable computer vision systems that utilize data-streaming concepts for processing of visual data streams. However, several challenges exist in building large-scale computer vision systems. For example, computer vision algorithms have different accuracy and speed profiles depending on the content, type, and speed of incoming data. Also, it is not clear how to adaptively tune these algorithms in large-scale systems. These challenges exist because we lack formal frameworks for building and optimizing large-scale visual processing. This paper presents formal methods and algorithms that aim to overcome these challenges and improve building and optimizing large-scale computer vision systems. We describe a formal algebra framework for the mathematical description of computer vision pipelines for processing image and video streams. The algebra naturally describes feedback control and provides a formal and abstract method for optimizing computer vision pipelines. We then show that a general optimizer can be used with the feedback-control mechanisms of our stream algebra to provide a common online parameter optimization method for computer vision pipelines.
- Open Access
Joint Spatial and Layer Attention for Convolutional Networks
In this paper, we propose a novel approach that learns to sequentially attend to different Convolutional Neural Networks (CNN) layers (i.e., ``what'' feature abstraction to attend to) and different spatial locations of the selected feature map (i.e., ``where'') to perform the task at hand. Specifically, at each Recurrent Neural Network (RNN) step, both a CNN layer and localized spatial region within it are selected for further processing. We demonstrate the effectiveness of this approach on two computer vision tasks: (i) image-based six degree of freedom camera pose regression and (ii) indoor scene classification. Empirically, we show that combining the ``what'' and ``where'' aspects of attention improves network performance on both tasks. We evaluate our method on standard benchmarks for camera localization (Cambridge, 7-Scenes, and TUM-LSI) and for scene classification (MIT-67 Indoor Scenes). For camera localization our approach reduces the median error by 18.8\% for position and 8.2\% for orientation (averaged over all scenes), and for scene classification it improves the mean accuracy by 3.4\% over previous methods.
Open AccessJoint Spatial and Layer Attention for Convolutional Networks
In this paper, we propose a novel approach that learns to sequentially attend to different Convolutional Neural Networks (CNN) layers (i.e., ``what'' feature abstraction to attend to) and different spatial locations of the selected feature map (i.e., ``where'') to perform the task at hand. Specifically, at each Recurrent Neural Network (RNN) step, both a CNN layer and localized spatial region within it are selected for further processing. We demonstrate the effectiveness of this approach on two computer vision tasks: (i) image-based six degree of freedom camera pose regression and (ii) indoor scene classification. Empirically, we show that combining the ``what'' and ``where'' aspects of attention improves network performance on both tasks. We evaluate our method on standard benchmarks for camera localization (Cambridge, 7-Scenes, and TUM-LSI) and for scene classification (MIT-67 Indoor Scenes). For camera localization our approach reduces the median error by 18.8\% for position and 8.2\% for orientation (averaged over all scenes), and for scene classification it improves the mean accuracy by 3.4\% over previous methods.
- Open Access
EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning
Over the last few years, deep learning techniques have yielded significant improvements in image inpainting. However, many of these techniques fail to reconstruct reasonable structures as they are commonly over-smoothed and/or blurry. This paper develops a new approach for image inpainting that does a better job of reproducing filled regions exhibiting fine details. We propose a two-stage adversarial model EdgeConnect that comprises of an edge generator followed by an image completion network. The edge generator hallucinates edges of the missing region (both regular and irregular) of the image, and the image completion network fills in the missing regions using hallucinated edges as a priori. We evaluate our model end-to-end over the publicly available datasets CelebA, Places2, and Paris StreetView, and show that it outperforms current state-of-the-art techniques quantitatively and qualitatively. Code and models available at: https://github.com/knazeri/edge-connect
Open AccessEdgeConnect: Generative Image Inpainting with Adversarial Edge Learning
Over the last few years, deep learning techniques have yielded significant improvements in image inpainting. However, many of these techniques fail to reconstruct reasonable structures as they are commonly over-smoothed and/or blurry. This paper develops a new approach for image inpainting that does a better job of reproducing filled regions exhibiting fine details. We propose a two-stage adversarial model EdgeConnect that comprises of an edge generator followed by an image completion network. The edge generator hallucinates edges of the missing region (both regular and irregular) of the image, and the image completion network fills in the missing regions using hallucinated edges as a priori. We evaluate our model end-to-end over the publicly available datasets CelebA, Places2, and Paris StreetView, and show that it outperforms current state-of-the-art techniques quantitatively and qualitatively. Code and models available at: https://github.com/knazeri/edge-connect
- Open Access
A Framework for Video-Driven Crowd Synthesis
We present a framework for video-driven crowd synthesis. Motion vectors extracted from input crowd video are processed to compute global motion paths. These paths encode the dominant motions observed in the input video. These paths are then fed into a behavior-based crowd simulation framework, which is responsible for synthesizing crowd animations that respect the motion patterns observed in the video. Our system synthesizes 3D virtual crowds by animating virtual humans along the trajectories returned by the crowd simulation framework. We also propose a new metric for comparing the "visual similarity" between the synthesized crowd and exemplar crowd. We demonstrate the proposed approach on crowd videos collected under different settings.
Open AccessA Framework for Video-Driven Crowd Synthesis
We present a framework for video-driven crowd synthesis. Motion vectors extracted from input crowd video are processed to compute global motion paths. These paths encode the dominant motions observed in the input video. These paths are then fed into a behavior-based crowd simulation framework, which is responsible for synthesizing crowd animations that respect the motion patterns observed in the video. Our system synthesizes 3D virtual crowds by animating virtual humans along the trajectories returned by the crowd simulation framework. We also propose a new metric for comparing the "visual similarity" between the synthesized crowd and exemplar crowd. We demonstrate the proposed approach on crowd videos collected under different settings.
- 16 April 2015
- Published by Springer Nature
- p. 316-331
Accelerating Cost Volume Filtering Using Salient Subvolumes and Robust Occlusion Handling
- 16 April 2015
- Published by Springer Nature
- p. 316-331
Accelerating Cost Volume Filtering Using Salient Subvolumes and Robust Occlusion Handling
- 11 April 2015
- Published by Springer Nature
- p. 314-329
Towards Efficient Feedback Control in Streaming Computer Vision Pipelines
- 11 April 2015
- Published by Springer Nature
- p. 314-329
Towards Efficient Feedback Control in Streaming Computer Vision Pipelines
- 29 August 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 37 (4) , 847-861
Stereo Reconstruction of Droplet Flight Trajectories
We developed a new method for extracting 3D flight trajectories of droplets using high-speed stereo capture. We noticed that traditional multi-camera tracking techniques fare poorly on our problem, in part due to the fact that all droplets have very similar shapes, sizes and appearances. Our method uses local motion models to track individual droplets in each frame. 2D tracks are used to learn a global, non-linear motion model, which in turn can be used to estimate the 3D locations of individual droplets even when these are not visible in any camera. We have evaluated the proposed method on both synthetic and real data and our method is able to reconstruct 3D flight trajectories of hundreds of droplets. The proposed technique solves for both the 3D trajectory of a droplet and its motion model concomitantly, and we have found it to be superior to 3D reconstruction via triangulation. Furthermore, the learned global motion model allows us to relax the simultaneity assumptions of stereo camera systems. Our results suggest that, even when full stereo information is available, our unsynchronized reconstruction using the global motion model can significantly improve the 3D estimation accuracy.
- 29 August 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 37 (4) , 847-861
Stereo Reconstruction of Droplet Flight Trajectories
We developed a new method for extracting 3D flight trajectories of droplets using high-speed stereo capture. We noticed that traditional multi-camera tracking techniques fare poorly on our problem, in part due to the fact that all droplets have very similar shapes, sizes and appearances. Our method uses local motion models to track individual droplets in each frame. 2D tracks are used to learn a global, non-linear motion model, which in turn can be used to estimate the 3D locations of individual droplets even when these are not visible in any camera. We have evaluated the proposed method on both synthetic and real data and our method is able to reconstruct 3D flight trajectories of hundreds of droplets. The proposed technique solves for both the 3D trajectory of a droplet and its motion model concomitantly, and we have found it to be superior to 3D reconstruction via triangulation. Furthermore, the learned global motion model allows us to relax the simultaneity assumptions of stereo camera systems. Our results suggest that, even when full stereo information is available, our unsynchronized reconstruction using the global motion model can significantly improve the 3D estimation accuracy.
- 1 January 2013
- Published by Springer Nature
- p. 67-82
Object Video Streams: A Framework for Preserving Privacy in Video Surveillance
- 1 January 2013
- Published by Springer Nature
- p. 67-82
Object Video Streams: A Framework for Preserving Privacy in Video Surveillance