Affine-Function Transformation-Based Object Matching for Vehicle Detection from Unmanned Aerial Vehicle Imagery

Cao, Shuang; Yu, Yongtao; Guan, Haiyan; Peng, Daifeng; Yan, Wanqian

doi:10.3390/rs11141708

Cited by 11 publications

(8 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A multiinstance SVM is then trained to classify from the density map derived from the positive regions. To deal with the scale and orientation variations, shadow, and partial occlusion, Cao et al present an affine-function transformation-based object matching framework [30]. Similar to the previous approach, superpixel segmentation is adopted to generate nonredundant patches, followed by detection and localization with a threshold matching cost.…”

Section: Related Workmentioning

confidence: 99%

VAID: An Aerial Image Dataset for Vehicle Detection and Classification

Lin

2020

IEEE Access

View full text Add to dashboard Cite

The availability of commercial UAVs and low-cost imaging devices has made the airborne imagery popular and widely available. The aerial images are now extensively used for many applications, especially in the area of intelligent transportation systems. In this work, we present a new aerial image dataset, VAID (Vehicle Aerial Imaging from Drone), for the development and evaluation of vehicle detection algorithms. It contains about 6,000 images captured under different traffic conditions, and annotated with 7 common vehicle categories for network training and testing. We compare the of vehicle detection results using the current state-of-the-art network architectures and various aerial image datasets. The experiments have demonstrated that training the networks using our VAID dataset can provide the best vehicle detection results.

show abstract

Section: Related Workmentioning

confidence: 99%

VAID: An Aerial Image Dataset for Vehicle Detection and Classification

Lin

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Jianqing et al [24] studied ground filtering and point clustering techniques in windy weather by attaching light detection and ranging to a fixed device and compared the performance with existing data processing algorithms. Shuang et al [25] studied the object matching framework based on affinefunction transformation for vehicle detection from the crewless aerial vehicle's camera image. This method effectively handles vehicles in various conditions such as scale change, direction change, shadow and partial occlusion.…”

Section: Introductionmentioning

confidence: 99%

A Study on Distance Measurement Module for Driving Vehicle Velocity Estimation in Multi-Lanes Using Drones

Lee

2021

Applied Sciences

View full text Add to dashboard Cite

A method of estimating driving vehicle information usually uses a speed gun and a fixed speed camera. Estimating vehicle information using the speed gun has a high risk of traffic accidents by the operator and the fixed speed camera is not efficient in terms of installation cost and maintenance. The existing driving vehicle information estimation method can only measure each lane’s driving vehicle information, so it is impossible to measure multi-lanes simultaneously with a single measuring device. This study develops a distance measurement module that can acquire driving vehicle information in multi-lanes simultaneously with a single system using a drone. The distance measurement module is composed of two LiDAR sensors to detect the driving vehicle in one lane. The drone is located above the edge of the road and each LiDAR sensor emits the front/rear point of the road measuring point to detect the driving vehicle. The driving vehicle velocity is estimated by detecting the driving vehicle’s detection distance and transit time through radiation, with the drone LiDAR sensor placed at two measurement points on the road. The drone LiDAR sensor radiates two measuring points on the road and estimates the velocity based on driving vehicle’s detection distance and driving time. As an experiment, the velocity accuracy of the drone driving vehicle is compared with the speed gun measurement. The vehicle velocity RMSE for the first and second lanes using drones is 0.75 km/h and 1.3 km/h, respectively. The drone and the speed gun’s average error probabilities are 1.2% and 2.05% in the first and second lanes, respectively. The developed drone is more efficient than existing driving vehicle measurement equipment because it can acquire information on the driving vehicle in a dark environment and a person’s safety.

show abstract

“…Real-time vehicle detection in aerial imagery has been an active research area in recent years [1]- [4]. Due to high altitudes in which aerial images are acquired, targets of interest (e.g., vehicles) contain fewer pixels than targets imaged at considerably lower elevations (e.g., building surveillance cameras, or traffic cameras), which significantly degrades detection performance.…”

Section: Introductionmentioning

confidence: 99%

Joint-SRVDNet: Joint Super Resolution and Vehicle Detection Network

et al. 2020

View full text Add to dashboard Cite

In many domestic and military applications, aerial vehicle detection and super-resolution algorithms are frequently developed and applied independently. However, aerial vehicle detection on superresolved images remains a challenging task due to the lack of discriminative information in the super-resolved images. To address this problem, we propose a Joint Super-Resolution and Vehicle Detection Network (Joint-SRVDNet) that tries to generate discriminative, high-resolution images of vehicles from low-resolution aerial images. First, aerial images are up-scaled by a factor of 4x using a Multi-scale Generative Adversarial Network (MsGAN), which has multiple intermediate outputs with increasing resolutions. Second, a detector is trained on super-resolved images that are upscaled by factor 4x using MsGAN architecture and finally, the detection loss is minimized jointly with the super-resolution loss to encourage the target detector to be sensitive to the subsequent super-resolution training. The network jointly learns hierarchical and discriminative features of targets and produces optimal super-resolution results. We perform both quantitative and qualitative evaluation of our proposed network on VEDAI, xView and DOTA datasets. The experimental results show that our proposed framework achieves better visual quality than the state-of-the-art methods for aerial super-resolution with 4x up-scaling factor and improves the accuracy of aerial vehicle detection.

show abstract

Affine-Function Transformation-Based Object Matching for Vehicle Detection from Unmanned Aerial Vehicle Imagery

Cited by 11 publications

References 59 publications

VAID: An Aerial Image Dataset for Vehicle Detection and Classification

VAID: An Aerial Image Dataset for Vehicle Detection and Classification

A Study on Distance Measurement Module for Driving Vehicle Velocity Estimation in Multi-Lanes Using Drones

Joint-SRVDNet: Joint Super Resolution and Vehicle Detection Network

Contact Info

Product

Resources

About