VirCap: Virtual Camera Exposure Control Based on Image Photometric Synthesis for Visual SLAM Application

Abstract

Mobile robots, such as quadrupedal and vehicular robots, are known for their high-speed movement and operation in environments with wide dynamic ranges. This property challenges the existing camera capture methods for visual applications, especially the visual simultaneous localization and mapping (SLAM) task, which requires a strong temporal continuity. Due to the limitations imposed by the camera hardware's control frequency and delay, camera exposure control methods cannot rapidly and stably publish high-quality images preventing oversaturation, background noise, and motion blur. In this article, we propose a novel image acquisition framework called VirCap, introducing image bracketing capture patterns to preserve more dynamic range information than a single image capture. By leveraging image photometric synthetic technology, VirCap enables a virtual camera exposure control (exposure time and analog gain), effectively decoupling the camera interaction from the control loop and facilitating more frequent exposure updates than traditional camera control methods. An exposure allocation strategy is also developed to balance motion blur and background noise, allowing VirCap to synthesize images of optimal quality that consider the robot's self-motion. Extensive experiments are conducted to demonstrate the efficiency and resilience of VirCap under extreme operating conditions for different visual SLAM systems.