Multi-object detection at night for traffic investigations based on improved SSD framework
Despite significant progress in vision-based detection methods, the task of detecting traffic objects at night remains challenging. Visual information of medium and small stationary objects is deteriorated due to poor lighting conditions. And the visual information is important for traffic investiga...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-11-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844022028584 |
| _version_ | 1811320597760704512 |
|---|---|
| author | Qiang Zhang Xiaojian Hu Yutao Yue Yanbiao Gu Yizhou Sun |
| author_facet | Qiang Zhang Xiaojian Hu Yutao Yue Yanbiao Gu Yizhou Sun |
| author_sort | Qiang Zhang |
| collection | DOAJ |
| description | Despite significant progress in vision-based detection methods, the task of detecting traffic objects at night remains challenging. Visual information of medium and small stationary objects is deteriorated due to poor lighting conditions. And the visual information is important for traffic investigations. For meeting the needs of night traffic investigations, this study focuses on presenting a nighttime multi-object detection framework based on Single Shot MultiBox Detector (SSD). Considering the need of traffic investigations, the applicable detection framework is presented for detecting traffic objects, especially medium and small stationary objects. In the framework, the Dense Convolutional Network (DenseNet) and deconvolutional layers are introduced to enhance the feature reuse, and the effectiveness of the optimization is finally verified. In this paper, qualitative and quantitative experiments are presented. The results show that our presented framework has better detection performance for medium and small stationary objects. Moreover, the results show that presented framework has better performance for nighttime traffic investigations at intersections. |
| first_indexed | 2024-04-13T13:00:45Z |
| format | Article |
| id | doaj.art-97a5cb7eafd54c45b2083b210fd6be06 |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-04-13T13:00:45Z |
| publishDate | 2022-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-97a5cb7eafd54c45b2083b210fd6be062022-12-22T02:45:54ZengElsevierHeliyon2405-84402022-11-01811e11570Multi-object detection at night for traffic investigations based on improved SSD frameworkQiang Zhang0Xiaojian Hu1Yutao Yue2Yanbiao Gu3Yizhou Sun4Jiangsu Key Laboratory of Urban ITS, Southeast University, China; Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies, Southeast University, China; School of Transportation, Southeast University, Southeast University Road #2, Nanjing, 211189, ChinaJiangsu Key Laboratory of Urban ITS, Southeast University, China; Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies, Southeast University, China; School of Transportation, Southeast University, Southeast University Road #2, Nanjing, 211189, China; Corresponding author.Jiangsu JITRI Deep Perception Technology Research Institute Co., Ltd, Wuxi, 214028, ChinaJiangsu JITRI Deep Perception Technology Research Institute Co., Ltd, Wuxi, 214028, ChinaDulwich College, London, UKDespite significant progress in vision-based detection methods, the task of detecting traffic objects at night remains challenging. Visual information of medium and small stationary objects is deteriorated due to poor lighting conditions. And the visual information is important for traffic investigations. For meeting the needs of night traffic investigations, this study focuses on presenting a nighttime multi-object detection framework based on Single Shot MultiBox Detector (SSD). Considering the need of traffic investigations, the applicable detection framework is presented for detecting traffic objects, especially medium and small stationary objects. In the framework, the Dense Convolutional Network (DenseNet) and deconvolutional layers are introduced to enhance the feature reuse, and the effectiveness of the optimization is finally verified. In this paper, qualitative and quantitative experiments are presented. The results show that our presented framework has better detection performance for medium and small stationary objects. Moreover, the results show that presented framework has better performance for nighttime traffic investigations at intersections.http://www.sciencedirect.com/science/article/pii/S2405844022028584Object detectionNight conditionSSDMedium objectSmall object |
| spellingShingle | Qiang Zhang Xiaojian Hu Yutao Yue Yanbiao Gu Yizhou Sun Multi-object detection at night for traffic investigations based on improved SSD framework Heliyon Object detection Night condition SSD Medium object Small object |
| title | Multi-object detection at night for traffic investigations based on improved SSD framework |
| title_full | Multi-object detection at night for traffic investigations based on improved SSD framework |
| title_fullStr | Multi-object detection at night for traffic investigations based on improved SSD framework |
| title_full_unstemmed | Multi-object detection at night for traffic investigations based on improved SSD framework |
| title_short | Multi-object detection at night for traffic investigations based on improved SSD framework |
| title_sort | multi object detection at night for traffic investigations based on improved ssd framework |
| topic | Object detection Night condition SSD Medium object Small object |
| url | http://www.sciencedirect.com/science/article/pii/S2405844022028584 |
| work_keys_str_mv | AT qiangzhang multiobjectdetectionatnightfortrafficinvestigationsbasedonimprovedssdframework AT xiaojianhu multiobjectdetectionatnightfortrafficinvestigationsbasedonimprovedssdframework AT yutaoyue multiobjectdetectionatnightfortrafficinvestigationsbasedonimprovedssdframework AT yanbiaogu multiobjectdetectionatnightfortrafficinvestigationsbasedonimprovedssdframework AT yizhousun multiobjectdetectionatnightfortrafficinvestigationsbasedonimprovedssdframework |