Informative image selection for crowdsourcing-based mobile location recognition
- 120 Downloads
With the prevalence of smartphones, the demand of recognizing the location through their camera and sensors is paid abundant attentions. For constructing a location recognition image database, the crowdsourcing technology is introduced to collect images associated with other sensory data. However, as abundant crowdsourced images evolve, it is essential to select high-quality images to decrease the burden of storage when designing an offline location recognition system directly on mobile devices. To address this problem, we propose an image selection framework, i.e., Informative image Selection Framework (ISF), considering both the diversity in spatial distribution and representativeness of images with high quality. First, for the images corresponding to the same object, we propose the Self-adaptive Space Clustering algorithm to group them into several clusters for maintaining high diversity of the image database. Second, for every cluster, we propose the Crucial Part Feature Detection algorithm to detect representative images. Extensive experiments demonstrate that ISF is effective and efficient for image selection, outperforming other similar image selection schemes around 5%.
KeywordsImage selection View direction Crowdsourcing Mobile location recognition
This work is supported by the National Natural Science Foundation of China under Grant No. 61332005 and No. 61502051, the Funds for Creative Research Groups of China under Grant No. 61421061, the Cosponsored Project of Beijing Committee of Education, and the Beijing Training Project for the Leading Talents in S&T (ljrc201502).
- 1.Fang, Q., Sang, J.T., Xu, C.S.: Giant: Geo-informative attributes for location recognition and exploration. In: ACM International Conference on Multimedia, pp. 13–22 (2013)Google Scholar
- 5.Wang, H., Zhao, D., Ma, H.D., Xu, H.Y., Hou, X.B.: Crowdsourcing based mobile location recognition with richer fingerprints from smartphone sensors. In: IEEE Conference on Parallel and Distributed Systems, pp. 156–163 (2015)Google Scholar
- 11.Li, X.W., Wu, C.C., Zach, C, Lazebnik, S., Frahm, J.M.: Modeling and recognition of landmark image collections using iconic scene graphs. In: European Conference on Computer Vision, pp. 427–440 (2008)Google Scholar
- 12.Wang H., Zhao D., Ma H., Xu H.: SSFS: A space-saliency fingerprint selection framework for crowdsourcing based mobile location recognition. In: Chen E., Gong Y., Tie Y. (eds) Advances in multimedia information processing - PCM 2016. PCM 2016. Lecture Notes in Computer Science, vol 9917, pp. 650–659. Springer, Cham (2016)Google Scholar
- 15.Ahn, L.V., Dabbish, L.: Labeling images with a computer game. In: Sigchi Conference on Human Factors in Computing Systems, pp. 319–326 (2004)Google Scholar
- 16.Wang, Y., Hu, W.J., Wu, Y.B., Cao, G.H.: SmartPhoto: a resource-aware crowdsourcing approach for image sensing with smartphones. In: International Symposium on Mobile Ad Hoc Networking and Computing, pp. 113–122 (2014)Google Scholar
- 17.Chen, H.H., Guo, B., Yu, Z.W., Chen, L.M.: CrowdPic: a multi-coverage picture collection framework for mobile crowd photographing. In: IEEE Conference on Ubiquitous Intelligence and Computing, pp. 68–76 (2015)Google Scholar
- 23.Muja, M., Lowe, D.G.: Fast approximate nearest neighbors with automatic algorithm configuration. In: International Conference on Computer Vision Theory and Applications, pp. 331–340 (2009)Google Scholar