Optimal scanning for faster object detection

Recent years have seen the development of fast and ac-curate algorithms for detecting objects in images. However, as the size of the scene grows, so do the running-times of these algorithms. If a 128 × 102 pixel image requires 20ms to process, searching for objects in a 1280 × 1024 image will take 2s. This is unsuitable under real-time operating constraints: by the time a frame has been processed, the ob-ject may have moved. An analogous problem occurs when controlling robot camera that need to scan scenes in search of target objects. In this paper, we consider a method for improving the run-time of general-purpose object-detection algorithms. Our method is based on a model of visual search in humans, which schedules eye fixations to maxi-mize the long-term information accrued about the location of the target of interest. The approach can be used to drive robot cameras that physically scan scenes or to improve the scanning speed for very large high resolution images. We consider the latter application in this work by simulat-ing a “digital fovea ” and sequentially placing it in vari-ous regions of an image in a way that maximizes the ex-pected information gain. We evaluate the approach using the OpenCV version of the Viola-Jones face detector. Af-ter accounting for all computational overhead introduced by the fixation controller, the approach doubles the speed of the standard Viola-Jones detector at little cost in accuracy. 1