Name
Title | ||
|---|---|---|
An Empirical Study of Object Detectors and Its Verification on the Embedded Object Detection Model Competition |
Abstract | ||
|---|---|---|
As one of the most active research fields in computer vision, the performance of object detection has been boosted by recent advancement of deep learning. However, performance improvements are often accompany with more resource consumption, which in turn restricts the application. There has been a rising interest in building object detectors that run well on embedded systems, i.e., with a better tradeoff among accuracy, speed, resource consumed, etc. To this end, we analyze popular object detectors, with an emphasis on taking typical evaluation metrics from the above aspects to assess both the selection of backbone network and the effects of input size. With these empirical studies, we propose to integrate MobileNet series into SSD to generate efficient yet accurate models and discuss their training tricks. The models are verified on the embedded object detection model competition held in conjunction with ICME 2020, where we gain the best accuracy on scooter detection. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/ICMEW46912.2020.9105978 | 2020 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) |
Keywords | DocType | ISSN |
Object detection,embedded system,deep learning,empirical study | Conference | 2330-7927 |
ISBN | Citations | PageRank |
978-1-7281-1486-6 | 0 | 0.34 |
References | Authors | |
3 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Junda Ren | 1 | 0 | 0.34 |
| Yongkun Du | 2 | 0 | 0.34 |
| Zhineng Chen | 3 | 192 | 25.29 |
| Fen Xiao | 4 | 29 | 6.87 |
| Caiyan Jia | 5 | 81 | 13.07 |
| Hongyun Bao | 6 | 0 | 0.68 |