CAMEL Dataset

Purpose

The purpose of this dataset is to provide a benchmark for visual-infrared object detection and tracking.

People

Professor Saibal Mukhopadhyay, PI
Professor Marilyn Wolf, Co-PI

Current Students:

Evan Gebhardt
Burhan Ahmad Mudassar
Priyabrata Saha
Yun Long
Minah Lee

Past Students:

Jong Hwan Ko
Taesik Na

Citation

If you find this data useful for your own work. please consider citing the following.

E. Gebhardt and M. Wolf, “CAMEL Dataset for Visual and Thermal Infrared Multiple Object Detection and Tracking,” IEEEInternational Conference on Advanced Video and Signal-based Surveillance (AVSS), 2018.

P. Saha, B. A Mudassar, and S. Mukhopadhyay, “Adaptive Control of Camera Modality with Deep Neural Network-Based Feedback for Efficient Object Tracking,” IEEEInternational Conference on Advanced Video and Signal-based Surveillance (AVSS), 2018.



Acknowledgement


DARPA Contract Number HR0011-17-2-0045


Contact


For questions, comments, or suggestions please contact evangeb41@gmail.com


Dataset


The image sequences are labeled 00000x.jpg or 00000x.png.


The annotation format is <Frame Number> <Track ID Number > <Annotation Class> <Bounding box top left x coordinate> <Bounding box top left y coordinate> <Bounding Box Width> <Bounding Box Height>


 








Sequence 1









Sequence 2









Sequence 3









Sequence 4









Sequence 5









Sequence 6









Sequence 7









Sequence 8









Sequence 9









Sequence 10









Sequence 11









Sequence 12









Sequence 13









Sequence 14









Sequence 15









Sequence 16









Sequence 17









Sequence 18









Sequence 19









Sequence 20









Sequence 21









Sequence 22









Sequence 23









Sequence 24









Sequence 25









Sequence 26









Sequence 27









Sequence 28









Sequence 29









Sequence 30









Benchmarks


Visual


Thermal Infrared