A Survey on Motion Models Used for Object Detection in Videos

Abstract

Object detection in videos is widely used in entertainment, robotics, surveillance etc. A major challenge in effective object detection is observed when there is occlusion, bad illumination or cluttered background. Besides, cameras do not provide any mechanism for detecting moving objects after capture. Researchers have proposed different methods for object detection in video frames, ranging from traditional to deep learning approaches. However, using the right method in the right situation for efficient and accurate detection is a concern. Even though deep learning has shown high accuracy in detection, the training and testing time and cost is a concern. In our research, we explore the best motion models for tracking objects in a video sequence. The characteristics of each model was analyzed and the results were compared using different types of videos. Our observations determine that depending on the quality of input video, traditional approaches show high accuracy in detection, comparable to state-of-the art methods.