Projects

Video analytics for agricultural machinery

The target of this project is to design and develop systems for farming machinery automation. Typical farming machines include tractors, combine harvesters, and choppers. Cameras installed inside the cockpit of these vehicles capture the surroundings. Using video analytics, the system interprets and logs information about nearby activities. This work was supported by the Open AG Technology and Systems (OATS) center.

Related papers:
1. He Liu, Amy R. Reibman, Aaron C. Ault, and James V. Krogmeier, Video-based Prediction for Header-height Control of a Combine Harvester, IEEE 2nd International Conference on Multimedia Information Processing and Retrieval (MIPR), 2019.
2. He Liu, Amy R. Reibman, Aaron C. Ault, and James V. Krogmeier, Video Classification of Farming Activities with Motion-Adaptive Feature Sampling, IEEE 20th International Workshop on Multimedia Signal Processing (MMSP), 2018.
3. He Liu, Amy R. Reibman, Aaron C. Ault, and James V. Krogmeier, Spatial Segmentation for Processing Videos for Farming Automation, Computers and Electronics in Agriculture, 2021.

Video analytics for dairy cow health assessment

In this project, we monitor a cow's health and well-being using surveillance camera videos. Multiple cameras are installed in a local dairy farm to observe cows walking as they exit the milking parlor. By analyzing the cow walking videos, we extract high-level information about each cow, such as identity, weight, and lameness. This work is supported by the Open AG Technology and Systems (OATS) center.

Related papers:
1. H. Liu, A. R. Reibman, J. P. Boerman, A cow structural model for video analytics of cow health, Computers and Electronics in Agriculture, 2020.
2. M. Ramesh, A. R. Reibman, and Jacquelyn P. Boerman, Eidetic recognition of cattle using keypoint alignment , Imaging and Multimedia Analytics at the Edge, Electronic Imaging, January 2023.

Video analytics for turkey welfare

Turkey production is very important in the United States. Production can be impacted by turkey welfare. However, changes in turkey welfare might not be completely visible to humans. Therefore, we work on building a robust system that is capable of tracking turkeys and identifying different types of aggregated behavior. Building such a system requires the usage of video analytics, computer vision, deep learning, and image processing techniques. By successfully analyzing and detecting changes in turkey welfare, farmers or researchers can take appropriate actions before problems further escalate.

Related papers:
1. S. Ju, M. A. Erasmus, A. R. Reibman, and F. Zhu, Video Tracking to Monitor Turkey Welfare , IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI), March 2020.
2. S. Ju, S. Mahapatra, M. A. Erasmus, A. R. Reibman, and F. Zhu, Turkey Behavior Identification System with a GUI Using Deep Learning and Video Analytics, Electronic Imaging, 2021.
3. S. Ju, M. A. Erasmus, F. Zhu, and A. R. Reibman, Turkey Behavior Identification Using Video Analytics And Object Tracking, IEEE International Conference on Image Processing (ICIP), 2021.

Image and video quality assessment for video analytics

Video quality and video content both affect the performance of emerging video-analytic tools, or tasks. Factors such as compression, lighting, and an individual's distinctiveness all have significant impact on task performance. In this project, we explore task-based video quality assessment.

Related papers:
1. H. Chen, E. J. Delp, and A. R. Reibman, Characterizing the Utility of Surveillance Video for Person Re-Identification , IEEE International Symposium on Technologies for Homeland Security, November 2019.
2. H. Chen, E. J. Delp, and A. R. Reibman, Estimating Image Quality for Person Re-Identification, IEEE 23rd International Workshop on Multimedia Signal Processing (MMSP), October 2021.
3. P. Singh, H. Chen, E. J. Delp, and A. R. Reibman, Evaluating Image Quality Estimators for Face Matching, IEEE 5th International Conference on Multimedia Information Processing and Retrieval (MIPR), August 2022.

Video analytics for assessing hand-hygiene

This project focuses on assessing the quality of hand-hygiene activities for the food safety industry. Effective hand-hygiene can reduce food contamination by human pathogens at during all stages of food handling. We use image processing, computer vision, and deep learning methods to build a system for hand-hygiene activity recognition. Analyzing the input hand-hygiene video, the system reports all the hand-hygiene actions performed by the user.

Related papers:
1. C. Zhong, A. R. Reibman, H. Mina Cordoba, and A. J. Deering, Hand-hygiene activity recognition in egocentric video , IEEE 21th International Workshop on Multimedia Signal Processing (MMSP), 2019.
2. C. Zhong, A. R. Reibman, H. A. Mina, and A. J. Deering, Multi-View Hand-Hygiene Recognition for Food Safety, Journal of Imaging, 2020.
3. C. Zhong, A. R. Reibman, H. A. Mina, and A. J. Deering, Designing a Computer-Vision Application: A Case Study for Hand-Hygiene Assessment in an Open-Room Environment, Journal of Imaging, 2021.
4. S. Ju, A. R. Reibman, and A. J. Deering Robust Hand Hygiene Monitoring for Food Safety using Hand Images , Imaging and Multimedia Analytics at the Edge, Electronic Imaging, January 2023.

Joint Video Compression and Analytics

Practical video analytics systems that perform computer vision tasks are widely used in critical real-world scenarios such as autonomous driving and public safety. These systems are usually deployed in bandwidth-constrained environments; hence, popular video compression algorithms like HEVC compress the inputs which are then passed onto modules that perform tasks like object detection, segmentation, and recognition sequentially. Video compression reduces transmission bandwidth but also degrades system performance. Here, we focus on understanding the effects of compression on the overall system performance using meaningful and interpretable evaluation procedures. We utilize this information to develop strategies that potentially reduce the impact of compression on system performance.

Related papers:
1. K. Tahboub, A. R. Reibman, and E. J. Delp, Accuracy Predicition for Pedestrian Detection , IEEE International Conference on Image Processing (ICIP), 2017.
2. P. Singh, E. J. Delp, and A. R. Reibman, Video-Analytics Task-Aware Quad-Tree Partitioning and Quantization For HEVC , IEEE International Conference on Image Processing (ICIP), 2022.
3. P. Singh, E. J. Delp, and A. R. Reibman, End-to-end Evaluation of Practical Video Analytics Systems for Face Detection and Recognition , Electronic Imaging (EI), 2023.