Robust and efficient post-processing for video object detection

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 stat-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.

Authors

• Alberto Sabater
• Luis Montesano
• Ana C. Murillo

Keywords

• Tracking
• Wearable computers
• Detectors
• Object detection
• Computational efficiency
• Object recognition
• Task analysis
• Video Object Detection
• Specific Detection
• Wearable Devices
• Detection In Images
• Video Data
• Still Images
• Post-processing Methods
• Video Recognition
• Specific Video
• Feature Maps
• Frame Rate
• Image Object
• Intersection Over Union
• Detection Model
• Bounding Box
• Object Classification
• Defocus
• Unfocused
• Object Instances
• Object Tracking
• Correct Detection
• Fast Motion
• Detection In Videos
• Pair Of Frames
• Bounding Box Coordinates
• Classification Confidence
• Consecutive Frames
• Optical Flow