Papers
2
Total Citations
3
H-Index
1
About
Tim Dolereit is a researcher at the forefront of embedded computer vision and intelligent marine monitoring. His work bridges the critical gap between real-time object recognition and low-power hardware constraints, a challenge central to autonomous driving and advanced driver-assistance systems (ADAS). In his highly cited 2018 paper, "A Configurable Framework for Hough-Transform-Based Embedded Object Recognition Systems," Dolereit introduced a novel, adaptable architecture that enables robust object detection on resource-constrained devices—a foundational contribution that has shaped subsequent embedded vision research. More recently, Dolereit has turned his expertise toward the aquaculture industry, pioneering non-invasive methods for fish health assessment. His 2024 work, "Fish Motion Estimation Using ML-based Relative Depth Estimation and Multi-Object Tracking," leverages machine learning to analyze fish swarm behavior from standard video feeds, overcoming previous limitations tied to specialized sensors or robotic proxies. By fusing relative depth estimation with multi-object tracking, he provides a scalable, cost-effective tool for monitoring fish welfare. With a growing citation footprint and a clear trajectory from embedded systems to applied marine biology, Dolereit exemplifies how foundational engineering can solve pressing real-world problems in both automotive safety and sustainable food production.
Research Focus
Key Achievements
Top Papers
- 1
- 2