Système de suivi de mouvement
|Abstract:||Small animal behavior is important for science and preclinical researchers; they want to know the effects of interventions in their natural life. For human diseases, rodents are used as models; studying rodent behavior is good for identifying and developing new drugs for psychiatric and neurological disorders. Animal monitoring can be processed and a large number of data can lead to better research result in a shorter time. This thesis introduces the rodents’ behavior tracking system based on computer vision techniques. In computer vision, object detection is scanning and searching for an object in an image or a video (which is just a sequence of images) but locating an object in successive frames of a video is called tracking. To find the position of an object in an image, we use object detection and object tracking together because tracking can help when detection fails and inversely. With this approach, we can track and detect any objects (mouse, headstage, or a ball). There is no dependency to the camera type. To find an object in an image we use the online AdaBoost algorithm, which is an object tracking algorithm and the Canny algorithm, which is an object detection algorithm together, then we check the results. If the online Adaboost algorithm could not find the object, we use the Canny algorithm to find the object. By comparing the results of our approach with the results of the online AdaBoost and Canny algorithms separately, we found that our approach can find the object in the image better than when we use these two algorithms separately. In this thesis, we will describe implemented object detection and tracking algorithms.|
|Document Type:||Mémoire de maîtrise|
|Open Access Date:||15 November 2019|
|Collection:||Thèses et mémoires|
All documents in CorpusUL are protected by Copyright Act of Canada.