Robust and efficient post-processing for video object detection
This work addresses video object detection for applications like autonomous driving and surveillance, offering an incremental improvement over existing post-processing methods.
The paper tackles the challenge of video object detection by introducing a novel post-processing pipeline that uses learning-based similarity evaluation between detections across frames, improving state-of-the-art results for fast-moving objects and achieving comparable performance to more intensive detectors with low resource requirements.
Object recognition in video is an important task for plenty of applications, including autonomous driving perception, surveillance tasks, wearable devices or IoT networks. Object recognition using video data is more challenging than using still images due to blur, occlusions or rare object poses. Specific video detectors with high computational cost or standard image detectors together with a fast post-processing algorithm achieve the current state-of-the-art. This work introduces a novel post-processing pipeline that overcomes some of the limitations of previous post-processing methods by introducing a learning-based similarity evaluation between detections across frames. Our method improves the results of state-of-the-art specific video detectors, specially regarding fast moving objects, and presents low resource requirements. And applied to efficient still image detectors, such as YOLO, provides comparable results to much more computationally intensive detectors.