Tiny Vehicle Detection for Mid-to-High Altitude UAV Images Based on Visual Attention and Spatial-Temporal Information

Abstract

Mid-to-high altitude Unmanned Aerial Vehicle (UAV) imagery can provide important remote sensing information between satellite and low altitude platforms, and vehicle detection in mid-to-high altitude UAV images plays a crucial role in land monitoring and disaster relief. However, the high background complexity of images and limited pixels of objects challenge the performance of tiny vehicle detection. Traditional methods suffer from poor adaptation ability to complex backgrounds, while deep neural networks (DNNs) have inherent defects in feature extraction of tiny objects with finite pixels. To address the issue above, this paper puts forward a vehicle detection method combining the DNNs-based and traditional methods for mid-to-high altitude UAV images. We first employ the deep segmentation network to exploit the co-occurrence of the road and vehicles, then detect tiny vehicles based on visual attention mechanism with spatial-temporal constraint information. Experimental results show that the proposed method achieves effective detection of tiny vehicles in complex backgrounds. In addition, ablation experiments are performed to inspect the effectiveness of each component, and comparative experiments on tinier objects are carried out to prove the superior generalization performance of our method in detecting vehicles with a limited size of 5 × 5 pixels or less.

SREDet: Semantic-Driven Rotational Feature Enhancement for Oriented Object Detection in Remote Sensing Images

“…Yang et al [19] and Li et al [39] utilize binary masks as supervisory information to spatially weight feature maps according to predicted probability maps, aiming to focus the model's attention on relevant areas. Yu et al [7] use a deep segmentation network to enhance the relationship between roads and vehicles, incorporating this into a visual attention mechanism with spatiotemporal constraints to detect small vehicles. Correspondingly, Yang et al [40] introduce multi-mask supervision to implicitly generate weight information, decoupling the features of different objects.…”

“…Oriented object detection in remote sensing images aims to utilize rotated bounding boxes to accurately determine the position and category of the object of interest [1,2]. It has gradually evolved into a significant domain within computer vision [3] and serves as a foundation task for various applications, such as smart cities, maritime rescue, and battlefield surveillance [4][5][6][7][8][9]. Due to the characteristics of overhead perspective and remote photography [10], remote sensing images typically have several characteristics: (1) objects are distributed with arbitrary orientations and variant appearances; (2) dense small-scale objects, such as vehicles and ships, often tend to cluster together closely; and (3) remote sensing images contain a significant amount of background information.…”

Drone-TOOD: A Lightweight Task-Aligned Object Detection Algorithm for Vehicle Detection in UAV Images

“…This integration not only improves the detection accuracy of the model but also opens up new ways for advanced image analysis in UAV applications. Yu R et al [22] proposed a multi-level micro vehicle detection framework (MTVD) for mid-and high-altitude drone images based on visual attention and spatiotemporal information, by using a segmentation network to extract road areas in the image and utilizing the attention mechanism. Improve the RSS algorithm with spatiotemporal information technology to suppress the impact of complex backgrounds on object detection and reduce false detections.…”

ASFF-YOLOv5: Multielement Detection Method for Road Traffic in UAV Images Based on Multiscale Feature Fusion

“…However, many scholars have improved the detection of small objects through strategies such as data enhancement, multiscale learning, contextual feature learning, and generative adversarial learning. For example, Yu et al [12] proposed a vehicle detection method for aerial vehicles based on a deep neural network and traditional method. This method uses a deep segmentation network to mine the symbiotic relationship between roads and vehicles and then detects small vehicles based on a visual attention mechanism of spatiotemporal constraint information.…”