Multi-Keyframe Propagation for Video Object Detection Based on Deep Learning

• 1、Institute of network technology, Beijing University of Posts and Telecommunications, Beijing City 100876

Abstract：Recently, with the development of deep learning, deep convolution neural networks have achieved great success on image recognition. The success promoted the extension and expansion of image recognition technology to the video field. Object detection is the most challenging problem in the field of computer vision. Now, the algorithms for image object detection problem are relatively mature and effective. However, there are few studies on video object detection. The video contains more information than the image. Based on DFF algorithm and FGFA algorithm, this paper presents a new algorithm, called MKP algorithm, which combines the advantages of DFF algorithm and FGFA algorithm. Experiments show that we can get models with different accuracy and rate by adjusting the parameters, so that the MKP algorithm can be applied to different scenarios and needs.

Keywords： feature extraction object detection optical flow feature propagation feature aggregation