Enhancing Video Analytics Accuracy via Real-time Automated Camera Parameter Tuning
Sibendu Paul, Kunal Rao, Giuseppe Coviello, Murugan Sankaradas, Oliver, Po, Y. Charlie Hu, Srimat T. Chakradhar

TL;DR
This paper introduces CamTuner, a reinforcement learning framework that dynamically adjusts non-automated camera parameters in real-time to improve video analytics accuracy under changing environmental conditions.
Contribution
It presents the first adaptive system for tuning camera settings to optimize analytics accuracy, incorporating a lightweight quality estimator and a virtual camera for fast RL training.
Findings
Increases detection of persons by 15.9% in enterprise parking lots.
Improves vehicle detection by up to 4.2% in traffic scenarios.
Enhances accuracy for automatic vehicle collision prediction.
Abstract
In Video Analytics Pipelines (VAP), Analytics Units (AUs) such as object detection and face recognition running on remote servers critically rely on surveillance cameras to capture high-quality video streams in order to achieve high accuracy. Modern IP cameras come with a large number of camera parameters that directly affect the quality of the video stream capture. While a few of such parameters, e.g., exposure, focus, white balance are automatically adjusted by the camera internally, the remaining ones are not. We denote such camera parameters as non-automated (NAUTO) parameters. In this paper, we first show that environmental condition changes can have significant adverse effect on the accuracy of insights from the AUs, but such adverse impact can potentially be mitigated by dynamically adjusting NAUTO camera parameters in response to changes in environmental conditions. We then…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsVideo Surveillance and Tracking Methods · Autonomous Vehicle Technology and Safety · Anomaly Detection Techniques and Applications
MethodsSarsa
