CNN-Based Obstacle Avoidance Using RGB-Depth Image Fusion

Chaymae El Mechal*, Najiba El Amrani El Idrissi, Mostefa Mesbah

*المؤلف المقابل لهذا العمل

نتاج البحث: Conference contribution


In the last few years, deep learning has attracted wide interest and achieved great success in many computer vision related applications, such as image classification, object detection, object tracking, pose estimation and action recognition. One specific application that can greatly benefit from the recent advance of deep learning is robot vision-based obstacle avoidance. Vision-based obstacle avoidance systems are mostly based on classification algorithms. Most of these algorithms use either color images or depth images as the main source of information. In this paper, the aim is to investigate whether using information extracted from both types of images simultaneously would give better performance than using each one separately. To do this, we chose the convolutional neural network (CNN) as the classifier and HSV-based method to achieve the fusion. We tested this approach using two widely used pre-trained CNN architectures, namely Resnet-50 and GoogLeNet using a dataset locally collected. The results indicate that the image fusion-based classification algorithm achieve a higher accuracy (91.3%) than the one based on depth images (80.4%) but lower than the one based on color images (93.7%). These results can be partly explained by the fact that the used classifiers were pre-trained using color image datasets.

اللغة الأصليةEnglish
عنوان منشور المضيفWITS 2020 - Proceedings of the 6th International Conference on Wireless Technologies, Embedded, and Intelligent Systems
المحررونSaad Bennani, Younes Lakhrissi, Ghizlane Khaissidi, Anass Mansouri, Youness Khamlichi
ناشرSpringer Science and Business Media Deutschland GmbH
عدد الصفحات10
رقم المعيار الدولي للكتب (المطبوع)9789813368927
المعرِّفات الرقمية للأشياء
حالة النشرPublished - 2022
منشور خارجيًانعم
الحدث6th International Conference on Wireless Technologies, Embedded and Intelligent Systems, WITS 2020 - fez, Morocco
المدة: أكتوبر ١٤ ٢٠٢٠أكتوبر ١٦ ٢٠٢٠

سلسلة المنشورات

الاسمLecture Notes in Electrical Engineering
مستوى الصوت745
رقم المعيار الدولي للدوريات (المطبوع)1876-1100
رقم المعيار الدولي للدوريات (الإلكتروني)1876-1119


Conference6th International Conference on Wireless Technologies, Embedded and Intelligent Systems, WITS 2020

ASJC Scopus subject areas

  • ???subjectarea.asjc.2200.2209???


أدرس بدقة موضوعات البحث “CNN-Based Obstacle Avoidance Using RGB-Depth Image Fusion'. فهما يشكلان معًا بصمة فريدة.

قم بذكر هذا