Pedestrian segmentation in infrared images based on local autocorrelation

Tao Wu; Shaogeng Zeng; Junjie Yang

doi:10.1117/12.2243727

Translator Disclaimer

29 August 2016 Pedestrian segmentation in infrared images based on local autocorrelation

Tao Wu, Shaogeng Zeng, Junjie Yang

Author Affiliations +

Proceedings Volume 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016); 100331J (2016) https://doi.org/10.1117/12.2243727
Event: Eighth International Conference on Digital Image Processing (ICDIP 2016), 2016, Chengu, China

Abstract

In order to select the optimal threshold for pedestrian segmentation in infrared images, a novel algorithm based on local autocorrelation is proposed. The algorithm calculates the local autocorrelation feature of a given image. Next, it constructs a new feature matrix based on this spatial correlation and the original grayscale. Then, it obtains an automatic threshold related with local combined features using the geometrical method based on histogram analysis. Finally, it extracts the image region of pedestrian and yields the binary result. It is indicated by the experiments that, the proposed method performs good result of pedestrian region extraction and thresholding, and it is reasonable and effective.

Citation Download Citation

Tao Wu, Shaogeng Zeng, and Junjie Yang "Pedestrian segmentation in infrared images based on local autocorrelation", Proc. SPIE 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016), 100331J (29 August 2016); https://doi.org/10.1117/12.2243727

ACCESS THE FULL ARTICLE