Learning to Control Camera Exposure via Reinforcement Learning

Deep Reinforcement Learning based Automatic Exposure Control (ours) Conventional Built-in Automatic Exposure Control Illumination Change (a) Automatic exposure control for sudden lighting changes # Features: 1504 # Features: 609 (1) Well-exposed image acquisition (2) Object detection (3) Feature extraction (b) Effectiveness on various vision applications (left: ours, right: built-in AE) Figure 1. Automatic camera exposure control via deep reinforcement learning. Our proposed method, named DRL-AE, trains an agent to control camera exposure parameters (i.e., exposure time and gain) to acquire well-exposed images with rapid convergence and real-time processing (1ms on a CPU device). The trained agent instantly converges within five frames under dramatic lighting change scenario (a) and affects the performance of various vision applications (b), compared to the camera built-in AE controller [17, 21].