How training data influence the recognition performance?
- Authors
- Chen, Y.; Rishi, S.; Sharma, A.; Shin, H.
- Issue Date
- 2019
- Publisher
- International Journal of Scientific and Technology Research
- Keywords
- Index Terms: Fusion network; Infrared; Small-sized pedestrian detection; Visible
- Citation
- International Journal of Scientific and Technology Research, v.8, no.12, pp.1340 - 1344
- Indexed
- SCOPUS
- Journal Title
- International Journal of Scientific and Technology Research
- Volume
- 8
- Number
- 12
- Start Page
- 1340
- End Page
- 1344
- URI
- https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/4563
- ISSN
- 2277-8616
- Abstract
- Eff ective fusion of multispectral images captured by visible and infrared cameras enables robust pedestrian detection under various surveillance situations (e.g., daytime and nighttime). However, the performance of detecting small-sized pedestrian instances is still not satisfactory, while small pedestrian detection is important for self-driving and drone vision. Therefore, our effort focuses on improving the detection performance of small-sized multispectral pedestrians which are relatively far from the camera. Since existing multispectral pedestrian datasets mainly consider the large size pedestrians of 50 or more pixels in height, we generate a multispectral pedestrian dataset, named HH (Hanyang and Huins), in which the pedestrian height is from 25 to 50 pixels. To balance the trade-off between the detection performance and speed, we investigate a fusion network to combine two single-shot detectors (SSDs) for the fusion of visible and infrared inputs. The proposed fusion network is trained on public KAIST and KAIST + HH datasets, respectively. From the experimental results, we can observe that the detection performance has been improved a lot by incorporating HH dataset into KAIST dataset for training. The network trained by the original KAIST dataset has only 7.40% average precision (AP). However, the results can be significantly improved to 88.32% by using KAIST + HH for training. This indicates that training images have a great impact on detection performance. © 2019, IJSTR.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - COLLEGE OF ENGINEERING SCIENCES > SCHOOL OF ELECTRICAL ENGINEERING > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/4563)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.