View on GitHub

Multispectral Pedestrian Benchmark

KAIST Multispectral Pedestrian Detection Benchmark [CVPR '15]

Download this project as a .zip file Download this project as a tar.gz file

Important notice, Our server is under maintenance. (Feb 07 14:30 KST ~ Feb 08 17:00 KST). We are sorry for your inconvenience.

KAIST Multispectral Pedestrian Detection Benchmark

By Soonmin Hwang, Jaesik Park, Namil Kim, Yukyung Choi, In So Kweon at RCV Lab. (KAIST) [Website] teaserImage

We developed imaging hardware consisting of a color camera, a thermal camera and a beam splitter to capture the aligned multispectral (RGB color + Thermal) images. With this hardware, we captured various regular traffic scenes at day and night time to consider changes in light conditions.

The KAIST Multispectral Pedestrian Dataset consists of 95k color-thermal pairs (640x480, 20Hz) taken from a vehicle. All the pairs are manually annotated (person, people, cyclist) for the total of 103,128 dense annotations and 1,182 unique pedestrians. The annotation includes temporal correspondence between bounding boxes like Caltech Pedestrian Dataset. More infomation can be found in our CVPR 2015 [paper] [Ext. Abstract].



  1. Clone this repository.
git clone --recursive
  1. First, download multispectral dataset.
cd rgbt-ped-detection/data/scripts
chmod +x & ./ & cd ../../


Run fetch_dataset_kaist_cvpr15.m in MATLAB.

  1. Altenatively, you can get direct links for the dataset here.

  2. Then just run acfDemoKAIST.m in MATLAB


Set00, Day-Campus Set04, Night-Road Set05, Night-Downtown


This repository includes an extension of Piotr’s Computer Vision Matlab Toolbox. We modify some codes to deal with 4-ch RGB+T images, e.g. ${PIOTR_TOOLBOX}/channels/chnsCompute.m. All the modifications are in libs/.


Experimental results

Many researchers struggle to improve pedestrian detection performance on our benchmark. If you are interested, please see these works.

Also, another researches to employ multi-modality are presented.


The horizontal lines divide the image types of the dataset (color, thermal and color-thermal). Note that our dataset is largest color-thermal dataset providing occlusion labels and temporal correspondences captured in a non-static traffic scenes.

Please see our Place Recognition Benchmark. [Link]


If you use our extended toolbox or dataset in your research, please consider citing:

	Author = {Soonmin Hwang and Jaesik Park and Namil Kim and Yukyung Choi and In So Kweon},
	Title = {Multispectral Pedestrian Detection: Benchmark Dataset and Baselines},
	Booktitle = {Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
	Year = {2015}