Moving Object Detection for Real-Time Applications

Detection of moving objects in video streams is the first relevant step of information extraction in many computer vision applications. Aside from the intrinsic usefulness of being able to segment video streams into moving and background components, detecting moving objects provides a focus of attention for recognition, classification, and activity analysis, making these later steps more efficient. We present some extensions to the method for moving object detection presented in H. Fujiyoshi and T. Kanade, (2004). Our main contributions are related to the pre-processing of intermediate results (transience maps), aimed at enhancing the accuracy of detection results, and to the parallelization of some of the most computationally intensive steps using SSE2 instructions, in order to enhance efficiency and allow for real-time applications.