We present a Polyhedral Scene Generator system which creates a random scene based on a few user parameters, renders the scene from random view points and creates a dataset containing the renderings and corresponding annotation files. We think that this generator will help to understand how a program could parse a scene if it had […]
Read MoreAbstract Scene Classification has been addressed with numerous techniques in the computer vision literature. However with the increasing size of datasets in the field, it has become difficult to achieve high accuracy in the context of robotics. We overcome this problem and obtain good results through our approach. In our approach, we propose to address […]
Read MorePaper (arXiv): Totally-Looks-Like: How Humans Compare, Compared to Machines Project website. Perceptual judgment of image similarity by humans relies on a rich internal representations ranging from low-level features to high-level concepts, scene properties and even cultural associations. Exist ing methods and datasets attempting to explain perceived similarity use stimuli which arguably do not cover the […]
Read MoreA. Rasouli, I. Kotseruba, and J. K. Tsotsos,“It’s Not All About Size: On the Role of Data Properties in Pedestrian Detection,” In Proc. European Conference on Computer Vision (ECCV) Workshop, 2018, pp. 210-225. A. Rasouli, I. Kotseruba, and J. K. Tsotsos,“Towards Social Autonomous Vehicles: Understanding Pedestrian-Driver Interactions,” In Proc. International Conference on Intelligent Transportation Systems […]
Read MoreAbstract Indoor Localization is a primary task for social robots. We are particularly interested in how to solve this problem for a mobile robot using primarily vision sensors. This work examines a critical issue related to generalizing approaches for static environments to dynamic ones: (i) it considers how to deal with dynamic users in the […]
Read More
Venue: ICCV 2017 Workshop: ACVR, Venice, 2017 Paper: Vision-Based Fallen Person Detection for the Elderly Project link: https://github.com/TsotsosLab/fallen-person-detector Abstract: Falls are serious and costly for elderly people. The Centers for Disease Control and Prevention of the US reports that millions of older people, 65 and older, fall each year at least once. Serious injuries such […]
Read More
Venue: CVR 2017, York University Abstract: Experiments on the visual cortex show existence of border ownership (BOS) neurons in V1 and V2. The responses of these neurons not only depend on the orientation of borders, but also on which side of the border the figure is. Neurophysiological studies show that BOS cell responses depend on […]
Read MoreBao Chen, Raghavendar Sahdev and John Tsotsos were co-recipients of the 2017 CIPPRS/ACTIRF Best Robotics Paper at the Conference on Computer and Robot Vision (CRV). Their paper describes efforts to develop a person following robot using stereo cameras. More details about the paper are available here.
Read MoreAbstract: In this paper we introduce a stereo vision based CNN tracker for a person following robot. The tracker is able to track a human in real time using an online convolutional neural network. Our approach enables the robot to follow a target under challenging situations like occlusions, appearance changes, pose changes, crouching, illumination changes […]
Read MoreThe Interaction of Target-Distractor Similarity and Visual Search Efficiency for Basic Features Authors: Calden Wloka, Sang-Ah Yoo, Rakesh Sengupta, and John K. Tsotsos Abstract: Visual search efficiency is commonly measured by the relationship between subject response time (RT) and display set size. Basic features are visual features for which a singleton target can be found […]
Read More