I was formerly with the
Vision and Robotics group where I completed my MSc under Prof. Martin Jagersand.
My master's thesis was mostly about high precision 2D tracking in natural images and its application to uncalibrated visual servoing.
As part of that project, I created a modular framework for registration based tracking that includes highly efficient C++ implementations of several appearance models, search methods and state space models - each combination thereof constituting a distinct tracker.
My research interests include computer vision and machine learning in general though I am particularly interested in the application of deep learning to vision problems like object detection, segmentation and tracking.
More info in my CV.
Determine the viability of iPSCs in early stages of growth by analyzing time-lapse microscopy images of cell cultures
Deep MDP: (May 2019 - April 2021): Supervisor: Dr. Nilanjan Ray, University of Alberta
Attempted to improve the performance of the MDP system and remove its heavy dependency on handcrafted features and heuristics by incorporating deep learning
Created an elegant abstraction to generalize the MDP framework to incorporate deep learning-based trackers, feature extractors and classifiers
Added support for cell tracking in microscopy images
Fence Damage Detection with Laser Imaging: (September 2020 - March 2021): Supervisor: Ken Brizel, ACAMP
Developed and analysed algorithms to detect small holes in fences using laser line detection based fence mask extraction and computer vision based hole detection
Animal and Human Detection with Deep Learning : (May-August 2018, January-April 2019): Supervisors: Dr. Nilanjan Ray, University of Alberta, Dr. Nehla Ghouaiel, ACAMP
Trained and tested 6 deep CNN based object detectors - RFCN, SSD, YOLO(1,2,3) and 3 variants of Faster RCNN - Inceptionv4, ResNet101, NAS - for detecting humans and 8 different types of animals
Trained and tested several instance segmentation methods like Mask RCNN and Sharpmask to generate realistic augmented data
Used Tensorflow, Darknet and Pytorch for implementation.
Created a ROS compatible application ready for deployment on an autonomous ATV.
Developed efficient ways to get compressed video data from the ATV to the GPU server.
Helped develop a fence damage detection algorithm using laser based line detection and unsupervised learning.
River Ice Segmentation with Deep Learning : (Jan 2018-May 2019): Supervisor: Dr. Nilanjan Ray, University of Alberta, Dr. Mark Loewen, University of Alberta
Adapted 4 state of the art deep architectures - UNet, SegNet, Deeplab and DenseNet - for dense pixelwise segmentation of river ice images
Used Keras, Theano and Tensorflow for implementation.
Improving model-based RL with Adaptive Rollout using Uncertainty Estimation : (Jan 2018-April 2018): Supervisor: Dr. Martha White, University of Alberta
Developed an algorithm to improve model based RL by automatically selecting the imagination rollout length for planning.
Used Pytorch for implementation
Adapted Python implementations of several baseline algorithms like Deep PILCO and NAF to be compatible with OpenAI Gym.
Created a system for tracking vehicles and pedestrians in real time traffic videos of roundabouts and intersections captured from UAV and pole mounted cameras.
Created a highly efficient python implementation of the MDP online multi object tracker using opencv, cuda and numpy to obtain a tenfold speed increase over the Matlab version and make it suitable for real time deployment.
Adapted an open source PyQt based graphical tool to perform integrated detection, tracking and semi automated labelling.
Modular Tracking Framework: A Unified Approach to Registration based Tracking : (Jan 2015-Feb 2017): Supervisor: Prof. Martin Jagersand, University of Alberta
Devised a novel way to study registration based trackers by decomposing them into three constituent
sub modules: appearance model, search method and state space model
Empirically tested different combinations of sub modules to produce novel and interesting observations and insights missing in each method's original paper due to limited testing.
Proposed two new appearance models and several new composite search methods to achieve a new state of the art in registration tracking.
Conducted experiments using four large datasets: TMT, UCSB, LinTrack and PAMI - with over 100,000 frames in all to ensure their statistical significance.
Created an open source tracking framework that can be used to reproduce all results and, owing to its efficient C++ implementation, also address practical tracking requirements.
Using Deep Learning techniques for 3D Object Recognition : (Jan 2014-April 2014): Supervisor: Prof. Dale Schuurmans, University of Alberta
Developed and tested several variants of the 6 hidden layer LeNet-5 architecture for classification of handwritten digits and 3D real world objects represented by the MNIST and NORB datasets respectively.
Used Matlab deep learning toolbox for implementation.
Multi Object Recognition in an Indoor Environment : (July 2012-Nov 2012): Supervisor: Prof. U.S. Tiwary, IIIT Allahabad
Implemented an object recognition system based on a hierarchical model of visual processing in the human visual cortex
System learns both invariance to object transformations and selectivity towards specific object features in an incremental manner, across several layers
Matlab was used for implementation and a custom created database of several common indoor objects was used for testing the system
Object Based Change Detection in Multi Temporal High Resolution Satellite Images : (July 2011-Nov 2011): Supervisor: Prof. Anupam Agrawal, IIIT Allahabad
Analyzed, debugged and documented an existing work based on multi feature fusion based change detection and also extended it with a hierarchical clustering based approach
The results of these were compared with each other as well as with existing pixel based methods
The system was tested on Google Earth images of IIIT-A taken in 2004 and 2008 and was found to give high accuracies of over 95% with both methodologies
Publications:
Sara Elkerdawy, Mostafa Elhoushi, Abhineet Singh, Hong Zhang and Nilanjan Ray, "To filter prune, or to layer prune, that is the question", accepted in 15th Asian Conference on Computer Vision (ACCV), December 2020 [pdf]
Sara Elkerdawy, Mostafa Elhoushi, Abhineet Singh, Hong Zhang and Nilanjan Ray, "One-Shot Layer-Wise Accuracy Approximation for Layer Pruning", in IEEE International Conference on Image Processing (ICIP), October 2020 [pdf]
Abhineet Singh, Hayden Kalke, Mark Loewen and Nilanjan Ray, "River Ice Segmentation with Deep Learning", in IEEE Transactions on Geoscience and Remote Sensing, February 2020 [pdf][supplementary][code]
Abhineet Singh, Marcin Pietrasik, Gabriell Natha, Nehla Ghouaiel, Ken Brizel and Nilanjan Ray, "Animal Detection in Man-made Environments", in the IEEE Winter Conference on Applications of Computer Vision (WACV), March 2020 [pdf][supplementary][code][labeling tool demo]
[wacv spotlight]
[poster]
Abhineet Singh and Martin Jagersand, "Modular Tracking Framework: A Fast Library for High Precision Tracking", IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), September 2017 [pdf][video][code]
Xuebin Qin, Shida He, Camilo Alfonso Perez Quintero, Abhineet Singh, Masood Dehghan, Martin Jagersand, "Real-Time Salient Closed Boundary Tracking via Line Segments Perceptual Grouping ", IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), September 2017 [pdf][video][code]
Mennatullah Siam, Abhineet Singh, Camilo Perez and Martin Jagersand, "4-DoF Tracking for Robot Fine Manipulation Tasks", in the 14th Conference on Computer and Robot Vision (CRV), May 2017 [pdf]
Abhineet Singh, Mennatullah Siam and Martin Jagersand, "Unifying Registration based Tracking: A Case Study with Structural Similarity", in the IEEE Winter Conference on Applications of Computer Vision (WACV), March 2017
[pdf][supplementary]
Abhineet Singh, Ankush Roy, Xi Zhang and Martin Jagersand, "Modular Decomposition and Analysis of Registration based Trackers", in 13th Conference on Computer and Robot Vision (CRV), 2016, pp.85-92, June 2016 [pdf][ppt]
Xi Zhang, Abhineet Singh and Martin Jagersand, "RKLT: 8 DOF Real-Time Robust Video Tracking Combing Coarse Ransac Features and Accurate Fast Template Registration", in 12th Conference on Computer and Robot Vision (CRV), 2015, pp.70-77, June 2015
[pdf][code]
Abdul Quaiyum Ansari, Madasu Hanmandlu, Jaspreet Kour and Abhineet Singh., "Online signature verification using segment-level fuzzy modelling", in IET Biometrics, vol.3, no.3, pp.113-127, Sept. 2014 [pdf]
Abhineet Singh and Anupam Agrawal., "An interactive framework for abandoned and removed object detection in video", in 2013 Annual IEEE India Conference (INDICON), pp.1-6, 13-15 Dec. 2013 [pdf]
Abhineet Singh, Savita Verma, Mangal Raj and Anupam Agrawal, "An Assessment of the Impact of Dimensionality Reduction on the Speed and Accuracy of Hyperspectral Image Classification", International Journal of Advanced Computer Research, ACCENTS Pub., Vol. 3, No. 3, pp. 436 - 441, Sept. 2013 [pdf]
