Facial and expression recognition for the blind using computer vision

Gemstone Team FACE

Leader Based Cyclic Pursuit

In this work a system of autonomous agents engaged in cyclic pursuit (under constant bearing (CB) strategy) is considered, for which one informed agent (the leader) also senses and responds to a stationary beacon. Building on the framework proposed in a previous work on beacon-referenced cyclic pursuit, necessary and suffi- cient conditions for the existence of circling equilibria in a system with one informed agent are derived, with discussion of stability and performance. In a physical testbed, the leader (robot) is equipped with a sound sensing apparatus composed of a real time embedded system, estimating direction of arrival of sound by an Interaural Level and Phase Difference Algorithm, using empirically determined phase and level signatures, and breaking front-back ambiguity with appropriate sensor placement. Furthermore a simple framework for implementing and evaluating the performance of control laws with the Robot Operating System (ROS) is proposed, demonstrated, and discussed.

Context Models for Understanding Images and Videos

A computer vision system that has to interact in natural language needs to understand the visual appearance of interactions between objects along with the appearance of objects themselves. Relationships between objects are frequently mentioned in queries of tasks like semantic image retrieval, image captioning, visual question answering and natural language object detection. Hence, it is essential to model context between objects for solving these tasks. In the first part of this thesis, we present a technique for detecting an object mentioned in a natural language query. Specifically, we work with referring expressions which are sentences that identify a particular object instance in an image. In many referring expressions, an object is described in relation to another object using prepositions, comparative adjectives, action verbs etc. Our proposed technique can identify both the referred object and the context object mentioned in such expressions. Context is also useful for incrementally understanding scenes and videos. In the second part of this thesis, we propose techniques for searching for objects in an image and events in a video. Our proposed incremental algorithms use the context from previously explored regions to prioritize the regions to explore next. The advantage of incremental understanding is restricting the amount of computation time and/or resources spent for various detection tasks. Our first proposed technique shows how to learn context in indoor scenes in an implicit manner and use it for searching for objects. The second technique shows how explicitly written context rules of one-on-one basketball can be used to sequentially detect events in a game.