Litcius/Paper detail

Slight Aware Enhancement Transformer and Multiple Matching Network for Real-Time UAV Tracking

Anping Deng, Guangliang Han, Dianbin Chen, Tianjiao Ma, Zhichao Liu

2023Remote Sensing17 citationsDOIOpen Access PDF

Abstract

Based on the versatility and effectiveness of the siamese neural network, the technology of unmanned aerial vehicle visual object tracking has found widespread application in various fields including military reconnaissance, intelligent transportation, and visual positioning. However, due to complex factors, such as occlusions, viewpoint changes, and interference from similar objects during UAV tracking, most existing siamese neural network trackers struggle to combine superior performance with efficiency. To tackle this challenge, this paper proposes a novel SiamSTM tracker that is based on Slight Aware Enhancement Transformer and Multiple matching networks for real-time UAV tracking. The SiamSTM leverages lightweight transformers to encode robust target appearance features while using the Multiple matching networks to fully perceive response map information and enhance the tracker’s ability to distinguish between the target and background. The results are impressive: evaluation results based on three UAV tracking benchmarks showed superior speed and precision. Moreover, SiamSTM achieves over 35 FPS on NVIDIA Jetson AGX Xavier, which satisfies the real-time requirements in engineering.

Topics & Concepts

Computer scienceBitTorrent trackerArtificial intelligenceTransformerComputer visionENCODEVideo trackingTracking (education)Matching (statistics)Artificial neural networkReal-time computingEye trackingObject (grammar)EngineeringVoltageElectrical engineeringStatisticsPsychologyMathematicsGeneChemistryPedagogyBiochemistryVideo Surveillance and Tracking MethodsInfrared Target Detection MethodologiesAdvanced Measurement and Detection Methods