Gradient-based Camera Exposure Control for Outdoor Mobile Platforms
We introduce a novel method to automatically adjust camera exposure for machine vision applications. Since most of machine vision algorithms heavily rely on low-level image features, we pay attention to the gradient information in order to determine a proper exposure level and make a camera capture important image features robust to illumination conditions. Additionally, we address a multi-camera system which is popular in robotics applications, and present a new control algorithm to achieve both the brightness consistency between adjacent cameras and the proper exposure level of each camera. We implement our prototype system with off-the-shelf machine vision cameras and demonstrate the effectiveness of our algorithms on several practical applications such as pedestrian detection, visual odometry, surround-view imaging, panoramic imaging, and stereo matching.
Overall framework
The overall framework of our camera exposure control. Our method adjusts camera exposure to maximize gradient information of captured images. We apply correction technique to simulate information changes by exposure variations, then update camera control parameters using a real-time feedback system. In addition, we balance the camera exposure of multi-camera using intensity differences between neighboring cameras.
Download slides (pptx) (Microsoft Power Point (>=2013) will be best to play this file.)
Download slides (pdf) (Pdf file does not include videos.)
