VISE

Hyewon Choi, Erkang Zhu, Arsala Bangash, Renée J. Miller
2019 Proceedings of the VLDB Endowment  
We present VISE, or Vehicle Image Search Engine, to support the fast search of similar vehicles from low-resolution traffic camera images. VISE can be used to trace and locate vehicles for applications such as police investigations when high-resolution footage is not available. Our system consists of three components: an interactive user-interface for querying and browsing identified vehicles; a scalable search engine for fast similarity search on millions of visual objects; and an image
more » ... ing pipeline that extracts feature vectors of objects from video frames. We use transfer learning technique to integrate state-of-the-art Convolutional Neural Networks with two different refinement methods to achieve high retrieval accuracy. We also use an efficient high-dimensional nearest neighbor search index to enable fast retrieval speed. In the demo, our system will offer users an interactive experience exploring a large database of traffic camera images that is growing in real time at 200K frames per day.
doi:10.14778/3352063.3352080 fatcat:rflm6emd6rhuply2bta3au6ite