FBRT-YOLO: Faster and Better for Real-Time Aerial Image Detection

TL;DR

FBRT-YOLO addresses real-time aerial image detection on resource-limited platforms by introducing two lightweight modules, FCM and MKP, to fuse shallow spatial cues with deep semantic features and to enhance multi-scale perception. By embedding FCM throughout the backbone and replacing the final downsampling with MKP, the approach achieves strong small-object localization with reduced parameters and FLOPs. Across VisDrone, UAVDT, and AI-TOD, FBRT-YOLO demonstrates superior accuracy-efficiency trade-offs, including notable AP gains and substantial reductions in model size and computation. This work offers a practical framework for deployable real-time aerial detectors with improved robustness in cluttered, small-object scenarios.

Abstract

Embedded flight devices with visual capabilities have become essential for a wide range of applications. In aerial image detection, while many existing methods have partially addressed the issue of small target detection, challenges remain in optimizing small target detection and balancing detection accuracy with efficiency. These issues are key obstacles to the advancement of real-time aerial image detection. In this paper, we propose a new family of real-time detectors for aerial image detection, named FBRT-YOLO, to address the imbalance between detection accuracy and efficiency. Our method comprises two lightweight modules: Feature Complementary Mapping Module (FCM) and Multi-Kernel Perception Unit(MKP), designed to enhance object perception for small targets in aerial images. FCM focuses on alleviating the problem of information imbalance caused by the loss of small target information in deep networks. It aims to integrate spatial positional information of targets more deeply into the network,better aligning with semantic information in the deeper layers to improve the localization of small targets. We introduce MKP, which leverages convolutions with kernels of different sizes to enhance the relationships between targets of various scales and improve the perception of targets at different scales. Extensive experimental results on three major aerial image datasets, including Visdrone, UAVDT, and AI-TOD,demonstrate that FBRT-YOLO outperforms various real-time detectors in terms of performance and speed.

Figures (5)

• Figure 1: The previous method overlooked the embedding of spatial information in deeper layers of the backbone network during feature extraction, leading to spatial semantic inconsistencies. Our method aims to transfer shallow spatial location information into deeper layers of the network during the feature extraction process, thereby enhancing the expression of semantic information.
• Figure 2: Our FBRT-YOLO is compared with other real-time detectors in terms of accuracy and efficiency on VisDrone dataset. The radius of the circle represents GFLOPs.
• Figure 3: Framework of FBRT-YOLO. FCM module is embedded into each stage of the backbone network to integrate spatial positional information into deeper semantic information. In the final (fourth) stage of the backbone network, MKP units are introduced along with multi-scale convolutions to enhance perception of targets at various scales. It's worth noting that MKP replaces the final downsampling layer while also reducing the corresponding detection heads.
• Figure 4: Visualization of the detection results and heatmaps on VisDrone. The highlighted areas represent the regions that the network is focusing on.
• Figure 5: Visualizations of the detection results of baseline and our proposed method under low light and similar background conditions on UAVDT. The blue boxes represent the prediction results using the baseline model, while the red boxes represent the prediction results using our method.