Vehicle Detection Under Unmanned Aerial Vehicle Based on Improved YOLOv3

In this study, the data obtained from the acoustic measurements were used to train a model based on logistic regression in order to detect a quadrotor’s vehicle in indoor environment. To simulate a real environment, we made sound recordings in a shopping center. The sounds related to two scenarios were recorded: only anthropic noise and anthropic noise with background music. Later, we reproduced these sounds in an indoor environment of the same size and characteristics as the shopping center. During the simulation test, a drone placed at different distances from the sound level meter was turned on at different speeds to identify their presence in complex acoustic scenarios. Subsequently, these measurements were used to implement a model based on logistic regression for the automatic detection of the unmanned aerial vehicle. Logistic regression is widely used in pattern recognition of the binary dependent variable. This model returns high value of accuracy (0.994), indicating a high number of correct detections. The results obtained in this study suggest the use of this tool for unmanned aerial vehicle detection applications.

Download Full-text

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

Remote Sensing ◽

10.3390/rs11141708 ◽

2019 ◽

Vol 11 (14) ◽

pp. 1708 ◽

Cited By ~ 2

Author(s):

Shuang Cao ◽

Yongtao Yu ◽

Haiyan Guan ◽

Daifeng Peng ◽

Wanqian Yan

Keyword(s):

Unmanned Aerial Vehicle ◽

Vehicle Detection ◽

Location Estimation ◽

Affine Function ◽

Response Elimination ◽

Object Matching ◽

Function Transformation ◽

Segmentation Strategy ◽

Aerial Vehicle ◽

Uav Images

Vehicle detection from remote sensing images plays a significant role in transportation related applications. However, the scale variations, orientation variations, illumination variations, and partial occlusions of vehicles, as well as the image qualities, bring great challenges for accurate vehicle detection. In this paper, we present an affine-function transformation-based object matching framework for vehicle detection from unmanned aerial vehicle (UAV) images. First, meaningful and non-redundant patches are generated through a superpixel segmentation strategy. Then, the affine-function transformation-based object matching framework is applied to a vehicle template and each of the patches for vehicle existence estimation. Finally, vehicles are detected and located after matching cost thresholding, vehicle location estimation, and multiple response elimination. Quantitative evaluations on two UAV image datasets show that the proposed method achieves an average completeness, correctness, quality, and F1-measure of 0.909, 0.969, 0.883, and 0.938, respectively. Comparative studies also demonstrate that the proposed method achieves compatible performance with the Faster R-CNN and outperforms the other eight existing methods in accurately detecting vehicles of various conditions.

Download Full-text

Real-Time Vehicle-Detection Method in Bird-View Unmanned-Aerial-Vehicle Imagery

Sensors ◽

10.3390/s19183958 ◽

2019 ◽

Vol 19 (18) ◽

pp. 3958

Author(s):

Seongkyun Han ◽

Jisang Yoo ◽

Soonchul Kwon

Keyword(s):

Real Time ◽

Unmanned Aerial Vehicle ◽

Detection Method ◽

Vehicle Detection ◽

Research Area ◽

Angular Distortion ◽

Background Information ◽

Feature Maps ◽

Detection Model ◽

Aerial Vehicle

Vehicle detection is an important research area that provides background information for the diversity of unmanned-aerial-vehicle (UAV) applications. In this paper, we propose a vehicle-detection method using a convolutional-neural-network (CNN)-based object detector. We design our method, DRFBNet300, with a Deeper Receptive Field Block (DRFB) module that enhances the expressiveness of feature maps to detect small objects in the UAV imagery. We also propose the UAV-cars dataset that includes the composition and angular distortion of vehicles in UAV imagery to train our DRFBNet300. Lastly, we propose a Split Image Processing (SIP) method to improve the accuracy of the detection model. Our DRFBNet300 achieves 21 mAP with 45 FPS in the MS COCO metric, which is the highest score compared to other lightweight single-stage methods running in real time. In addition, DRFBNet300, trained on the UAV-cars dataset, obtains the highest AP score at altitudes of 20–50 m. The gap of accuracy improvement by applying the SIP method became larger when the altitude increases. The DRFBNet300 trained on the UAV-cars dataset with SIP method operates at 33 FPS, enabling real-time vehicle detection.

Download Full-text