Application of Deep Learning | Vision-Based Discernment and Counting of Vehicles inLow Illumination Using Deep Learning

Shafiulla Basha Shaik (u. a.)

ISBN 10: 6204742426 / ISBN 13: 9786204742427

Published by LAP LAMBERT Academic Publishing, 2022

About this Item

Application of Deep Learning | Vision-Based Discernment and Counting of Vehicles inLow Illumination Using Deep Learning | Shafiulla Basha Shaik (u. a.) | Taschenbuch | Englisch | 2022 | LAP LAMBERT Academic Publishing | EAN 9786204742427 | Verantwortliche Person für die EU: preigu GmbH & Co. KG, Lengericher Landstr. 19, 49078 Osnabrück, mail[at]preigu[dot]de | Anbieter: preigu.

Seller Inventory # 121351693

Bibliographic Details

• Title: Application of Deep Learning | Vision-Based Discernment and Counting of Vehicles inLow Illumination Using Deep Learning
• Publisher: LAP LAMBERT Academic Publishing
• Publication Date: 2022
• Language: English
• ISBN 10: 6204742426
• ISBN 13: 9786204742427
• Binding: Taschenbuch
• Condition: Neu
• Dimensions: 220W x 150H x 8D millimeters 220 millimeters width by 150 millimeters height by 8 millimeters depth
• Weight: 179 grams
• Seller catalogs:
  • Bücher

About this title

Synopsis

The intelligent transportation system has received a lot of attention in recent years. Vehicle detection is an important task in this area where vehicle counting and classification are two important applications. Taking the size of vehicles and illumination factor into consideration the detection remains a challenge. To overcome the above problem we propose aVision-Based Discernment and Counting of Vehicles in Low Illumination Using Deep Learning, In the proposed system, we enhance the low illumination image using the Dual-channel prior-based method. By using the segmentation method the highway road is first extracted and biased into two areas namely remote area and proximal area. Here we use the YOLOv3 network, by placing the above two areas in this network, we can detect the type and position of the vehicle. Finally, by using the ORB algorithm we can judge the direction of the vehicle and obtain a number of different vehicles. The results obtained are such that the accurate count of vehicles especially for small-sized vehicles in low illumination.