Evaluation of stereo matching for mobile platforms with applications for assisting the visually impaired

stereo matching;mobile devices;visually impaired assistance

Chidester, Benjamin Wilson ; Do ; Minh N.

关键词: stereo matching;    mobile devices;    visually impaired assistance;   

Others  :  https://www.ideals.illinois.edu/bitstream/handle/2142/46598/Benjamin_Chidester.pdf?sequence=1&isAllowed=y

美国|英语

来源: The Illinois Digital Environment for Access to Learning and Scholarship

【 摘 要 】

The rising interest in immersive entertainment and enhanced image and video content, along with the development of stereo cameras for mobileplatforms, motivates the presented evaluation of stereo matching algorithmsfor mobile devices. This work investigates this potential for stereo matchingon a mobile device for real-time applications, in terms of computation timeand quality of depth inference. Several algorithms are tested on an Androidtablet housing a Tegra 3 processor using imagescaptured from the on-board consumer-grade cameras. Despite distortions incurred by the lower quality cameras and the computationalconstraints of a tablet, results show that a simpleblock matching approach can perform reasonable inference at a rate of 10 frames-per-second. Other methods are shown to be too computationally demandingfor real-time applications, as even the fastest alternative local method, usingadaptive support weights, requires upto 20 seconds per frame on a 320x360 image. Results also show the impact oflower quality ``real-world'' images on inference performance on algorithms.Additionally, real-time stereo matching on a mobile device is applied to a novel application of assisting the visually impaired with navigation. A system is proposedusing a simple block matching algorithm that infers the depth of the scene and communicates the presence of obstacles via soundto the user. The system is housed entirely within the mobile device,overcoming a primary hindrance of many users of assistive technology. The use of a mobile device also allows for an intuitive, interactiveexperience for the user with the depth information directly viathe touch screen of the device. This system demonstrates the addedfunctionality of real-time depth estimation on a mobile device and the potential for aiding the visually impaired with navigation.