Implementation and optimization of image acquisition with smartphones in computer vision

Abstract

With many emerging function modules, such as image acquisition, front-end local processing, wireless transmission and so on, the smartphone becomes a major front-end hardware in the mobile-cloud computer vision system. However, due to the limitations of local resources and camera performance, there are many problems in image acquisition with smartphones. For example, the images are not as clear as those captured by professional camera equipment. And the performance of image acquisition is much more sensitive to background procedures and environment. These shortcomings have brought great challenges in terms of accuracy and delay in computer vision. In this paper, the Resolution Adaptive Algorithm (RAA) is proposed to select the optimal resolution for image acquisition in different situations. Furthermore, in order to improve the efficiency of local resources and reduce the processing delay, a low-quality image filtered method is presented to delete the invalid images. In our experiment, the average delay between image acquisition and display is about 100ms, which meets the requirement of detection in real time.