Encoder-Decoder Approach toward Vehicle Detection

Title

Encoder-Decoder Approach toward Vehicle Detection

Creator

Deb P.; Kumar S.; Preethi N.

Description

Vehicle Detection algorithms run on deep neural networks. But one problem arises, when the vehicle scale keeps on changing then we may get false detection or even sometimes no detection at all, especially when the object size is tiny. Then algorithms like CNN, fast-RCNN, and faster-RCNN have a high probability of missed detection. To tackle this situation YOLOv3 algorithm is being used. In the codec module, a multi-level feature pyramid is added to resolve multi-scale vehicle detection problems. The experiment was carried out with the KITTI dataset and it showed high accuracy in several environments including tiny vehicle objects. YOLOv3 was able to meet the application demand, especially in traffic surveillance Systems. Grenze Scientific Society, 2023.

Source

14th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2023, Vol-2023-June, pp. 1-6.

Date

2023-01-01

Publisher

Grenze Scientific Society

Subject

codec; convolutional neural network; moving object detection; Surveillance video; tracking; vehicle detection; YOLOv3

Coverage

Deb P., Department of Data Science, Christ University Lavasa, Pune, India; Kumar S., Department of Data Science, Christ University Lavasa, Pune, India; Preethi N., Department of Data Science, Christ University Lavasa, Pune, India

Rights

Restricted Access

Relation

0

Format

Online

Language

English

Type

Conference paper

Identifier

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85174281339&partnerID=40&md5=dc3e0129960322c3647fce9322212e48