Object/Scene Recognition Based on a Directional Pixel Voting Descriptor
Open Access
- 11 September 2024
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 14 (18) , 8187
Abstract
Detecting objects in images is crucial for several applications, including surveillance, autonomous navigation, augmented reality, and so on. Although AI-based approaches such as Convolutional Neural Networks (CNNs) have proven highly effective in object detection, in scenarios where the objects being recognized are unknow, it is difficult to generalize an AI model for such tasks. In another trend, feature-based approaches like SIFT, SURF, and ORB offer the capability to search any object but have limitations under complex visual variations. In this work, we introduce a novel edge-based object/scene recognition method. We propose that utilizing feature edges, instead of feature points, offers high performance under complex visual variations. Our primary contribution is a directional pixel voting descriptor based on image segments. Experimental results are promising; compared to previous approaches, ours demonstrates superior performance under complex visual variations and high processing speed.Keywords
This publication has 33 references indexed in Scilit:
- FPGA-SoC implementation of YOLOv4 for flying-object detectionJournal of Real-Time Image Processing, 2024
- Unmanned aerial vehicle (UAV) object detection algorithm based on keypoints representation and rotated distance-IoU lossJournal of Real-Time Image Processing, 2024
- TinyEmergencyNet: a hardware-friendly ultra-lightweight deep learning model for aerial scene image classificationJournal of Real-Time Image Processing, 2024
- An RGB-D SLAM algorithm based on adaptive semantic segmentation in dynamic environmentJournal of Real-Time Image Processing, 2023
- BIM-based indoor mobile robot initialization for construction automation using object detectionAutomation in Construction, 2022
- Maximum entropy scaled super pixels segmentation for multi-object detection and scene recognition via deep belief networkMultimedia Tools and Applications, 2022
- Region-based adaptive association learning for robust image scene recognitionThe Visual Computer, 2022
- An efficient technique for object recognition using Shi-Tomasi corner detection algorithmSoft Computing, 2020
- Object detection and classification: a joint selection and fusion strategy of deep convolutional neural network and SIFT point featuresMultimedia Tools and Applications, 2018
- All-hardware SIFT implementation for real-time VGA images feature extractionJournal of Real-Time Image Processing, 2018