Redirigiendo al acceso original de articulo en 21 segundos...
Inicio  /  Algorithms  /  Vol: 14 Par: 7 (2021)  /  Artículo
ARTÍCULO
TITULO

Knowledge-Driven Network for Object Detection

Yundong Wu    
Jiajia Liao    
Yujun Liu    
Kaiming Ding    
Shimin Li    
Zhilin Zhang    
Guorong Cai and Jinhe Su    

Resumen

Object detection is a challenging computer vision task with numerous real-world applications. In recent years, the concept of the object relationship model has become helpful for object detection and has been verified and realized in deep learning. Nonetheless, most approaches to modeling object relations are limited to using the anchor-based algorithms; they cannot be directly migrated to the anchor-free frameworks. The reason is that the anchor-free algorithms are used to eliminate the complex design of anchors and predict heatmaps to represent the locations of keypoints of different object categories, without considering the relationship between keypoints. Therefore, to better fuse the information between the heatmap channels, it is important to model the visual relationship between keypoints. In this paper, we present a knowledge-driven network (KDNet)?a new architecture that can aggregate and model keypoint relations to augment object features for detection. Specifically, it processes a set of keypoints simultaneously through interactions between their local and geometric features, thereby allowing the modeling of their relationship. Finally, the updated heatmaps were used to obtain the corners of the objects and determine their positions. The experimental results conducted on the RIDER dataset confirm the effectiveness of the proposed KDNet, which significantly outperformed other state-of-the-art object detection methods.

 Artículos similares

       
 
Majdi Sukkar, Madhu Shukla, Dinesh Kumar, Vassilis C. Gerogiannis, Andreas Kanavos and Biswaranjan Acharya    
Effective collision risk reduction in autonomous vehicles relies on robust and straightforward pedestrian tracking. Challenges posed by occlusion and switching scenarios significantly impede the reliability of pedestrian tracking. In the current study, w... ver más
Revista: Information

 
Samuel de Oliveira, Oguzhan Topsakal and Onur Toker    
Automated Machine Learning (AutoML) is a subdomain of machine learning that seeks to expand the usability of traditional machine learning methods to non-expert users by automating various tasks which normally require manual configuration. Prior benchmark... ver más
Revista: Information

 
Ali Dorosti, Ali Asghar Alesheikh and Mohammad Sharif    
Advancements in navigation and tracking technologies have resulted in a significant increase in movement data within road networks. Analyzing the trajectories of network-constrained moving objects makes a profound contribution to transportation and urban... ver más
Revista: Information

 
Kun Zhang, Pengbo Chang, Jianxi Ren, Zheng Liu and Ke Wang    
The fractured rock mass in the western cold region is affected by freezing and thawing disasters and is prone to local damage and fracture along the fissures? ends. The fatigue damage induced by repeated frost heave and traffic loads seriously endangers ... ver más
Revista: Applied Sciences

 
Xinmin Li, Yingkun Wei, Jiahui Li, Wenwen Duan, Xiaoqiang Zhang and Yi Huang    
Object detection in unmanned aerial vehicle (UAV) images has become a popular research topic in recent years. However, UAV images are captured from high altitudes with a large proportion of small objects and dense object regions, posing a significant cha... ver más
Revista: Applied Sciences