14 December 2015 Real-time detection of generic objects using objectness estimation and locally adaptive regression kernels matching
Author Affiliations +
Proceedings Volume 9812, MIPPR 2015: Automatic Target Recognition and Navigation; 98120K (2015) https://doi.org/10.1117/12.2205147
Event: Ninth International Symposium on Multispectral Image Processing and Pattern Recognition (MIPPR2015), 2015, Enshi, China
Abstract
Our purpose is to develop a detection algorithm capable of searching for generic interest objects in real time without large training sets and long-time training stages. Instead of the classical sliding window object detection paradigm, we employ an objectness measure to produce a small set of candidate windows efficiently using Binarized Normed Gradients and a Laplacian of Gaussian-like filter. We then extract Locally Adaptive Regression Kernels (LARKs) as descriptors both from a model image and the candidate windows which measure the likeness of a pixel to its surroundings. Using a matrix cosine similarity measure, the algorithm yields a scalar resemblance map, indicating the likelihood of similarity between the model and the candidate windows. By employing nonparametric significance tests and non-maxima suppression, we detect the presence of objects similar to the given model. Experiments show that the proposed detection paradigm can automatically detect the presence, the number, as well as location of similar objects to the given model. The high quality and efficiency of our method make it suitable for real time multi-category object detection applications.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Zhihui Zheng, Zhihui Zheng, Lei Gao, Lei Gao, Liping Xiao, Liping Xiao, Bin Zhou, Bin Zhou, Shibo Gao, Shibo Gao, } "Real-time detection of generic objects using objectness estimation and locally adaptive regression kernels matching", Proc. SPIE 9812, MIPPR 2015: Automatic Target Recognition and Navigation, 98120K (14 December 2015); doi: 10.1117/12.2205147; https://doi.org/10.1117/12.2205147
PROCEEDINGS
6 PAGES


SHARE
Back to Top