Camera Exposure Control for Robust Robot Vision with Noise-Aware Image Quality Assessment

Abstract

In this paper, we propose a noise-aware exposure control algorithm for robust robot vision. Our method aims to capture the best-exposed image which can boost the performance of various computer vision and robotics tasks. For this purpose, we carefully design an image quality metric which captures complementary quality attributes and ensures light-weight computation. Specifically, our metric consists of a combination of image gradient, entropy, and noise metrics. The synergy of these measures allows preserving sharp edge and rich texture in the image while maintaining a low noise level. Using this novel metric, we propose a real-time and fully automatic exposure and gain control technique based on the Nelder-Mead method. To illustrate the effectiveness of our technique, a large set of experimental results demonstrates higher qualitative and quantitative performances when compared with conventional approaches.

Auto-Exposure Algorithm for Enhanced Mobile Robot Localization in Challenging Light Conditions

“…Another way to limit sensitivity to noise was proposed in [ 18 ]. As detailed in Section 1.1 , the authors introduced the quality metric ( Figure 9 e).…”

“…This approach still does not directly relate metric values to VO performance. Shin [ 18 ] uses an approach which is closest to this work by directly comparing the absolute pose error associated with images selected according to the different metrics. The authors conclude that the quality metric is a better proxy of VO performance as the best images predicted by other metrics tend to be highly noisy.…”

“…As an alternative to Kim’s weighted gradient, Shin [ 18 ] proposed that the noise of an image ( ) be directly approximated as where and are the entry of binary matrices, respectively, masking out the non-homogeneous and the saturated regions of the image, is the number of pixels that are both homogeneous and unsaturated, and is the noise estimation kernel proposed by Immerkaer [ 24 ]. The approximation of the image noise is then incorporated in a hybrid image quality metric defined as where and are weighting factors, and is the standard deviation of the gradient information metric evaluated individually over each cell of a grid.…”

“…The approximation of the image noise is then incorporated in a hybrid image quality metric defined as where and are weighting factors, and is the standard deviation of the gradient information metric evaluated individually over each cell of a grid. The present work uses the authors’ original values of and proposed in [ 18 ].…”

“…While purely reactive approaches (e.g., [ 12 , 13 , 18 ]) do not require any characterization of the camera, they do require the slow process of sampling real-world images to converge. Instead, predictive AE algorithms use a model to predict the effect of future exposure parameters on the optimization metric.…”