Papers
1
Total Citations
7
H-Index
1
About
Dae-Hee Park is a researcher focused on advancing computer vision and robotics, with a particular emphasis on addressing real-world perceptual challenges in indoor environments. His work centers on improving object and person detection systems, especially in scenarios where environmental factors—such as mirror reflections—can degrade performance. Park’s most cited paper, "Identifying Reflected Images From Object Detector in Indoor Environment Utilizing Depth Information" (2020), tackles a critical problem for service robots: the confusion caused by reflected virtual images. By leveraging 3D depth information, he proposed a real-time method to distinguish real objects from their reflections, significantly enhancing detection reliability. This contribution has garnered 7 citations, reflecting its relevance to the robotics and computer vision communities. Park’s research bridges the gap between theoretical detection algorithms and practical deployment in dynamic, cluttered spaces, making his work valuable for developers of autonomous systems. His approach underscores the importance of multimodal sensing—combining visual and depth data—to overcome limitations of traditional 2D image-based detectors. For students and researchers exploring robust perception in robotics, Park’s work offers a clear example of how environmental context can be harnessed to improve machine vision.
Research Focus
Key Achievements
Top Papers
- 1