A Novel Vehicle Detection Method With High Resolution Highway Aerial Image

Zheng, Zezhong; Zhou, Guoqing; Wang, Yong; Liu, Yalan; Li, Xiaowen; Wang, Xiaoting; Jiang, Ling

doi:10.1109/jstars.2013.2266131

Cited by 70 publications

(63 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For traditional methods, some researchers use the road database as an a priori knowledge guide to detect vehicles [3,4,25], which is limited to special scenes covered by the road map database. In recent years, due to the advance of the machine learning technique, many approaches consider object detection as a region-of-interest (RoI) classification problem.…”

Section: Vehicle Detection Methods For Aerial Imagesmentioning

confidence: 99%

Arbitrary-Oriented Vehicle Detection in Aerial Imagery with Single Convolutional Neural Networks

et al. 2017

View full text Add to dashboard Cite

Vehicle detection with orientation estimation in aerial images has received widespread interest as it is important for intelligent traffic management. This is a challenging task, not only because of the complex background and relatively small size of the target, but also the various orientations of vehicles in aerial images captured from the top view. The existing methods for oriented vehicle detection need several post-processing steps to generate final detection results with orientation, which are not efficient enough. Moreover, they can only get discrete orientation information for each target. In this paper, we present an end-to-end single convolutional neural network to generate arbitrarily-oriented detection results directly. Our approach, named Oriented_SSD (Single Shot MultiBox Detector, SSD), uses a set of default boxes with various scales on each feature map location to produce detection bounding boxes. Meanwhile, offsets are predicted for each default box to better match the object shape, which contain the angle parameter for oriented bounding boxes' generation. Evaluation results on the public DLR Vehicle Aerial dataset and Vehicle Detection in Aerial Imagery (VEDAI) dataset demonstrate that our method can detect both the location and orientation of the vehicle with high accuracy and fast speed. For test images in the DLR Vehicle Aerial dataset with a size of 5616 × 3744, our method achieves 76.1% average precision (AP) and 78.7% correct direction classification at 5.17 s on an NVIDIA GTX-1060.

show abstract

Section: Vehicle Detection Methods For Aerial Imagesmentioning

confidence: 99%

Arbitrary-Oriented Vehicle Detection in Aerial Imagery with Single Convolutional Neural Networks

et al. 2017

View full text Add to dashboard Cite

show abstract

“…As can be seen from Figure 4, the image is smoothed and the boundaries of vehicles are well preserved. In the PAN image, vehicles appear to be elliptical blobs, and the idea of a blob detection algorithm for vehicle detection has been attempted [5,7]. In Zheng's work [5], classical top-hat transformation is used to identify moving vehicles in very high resolution aerial image (0.15 m).…”

Section: Vehicle Candidate Location Extractionmentioning

confidence: 99%

“…Typical vehicles have a length of 15-30 pixels, and then, the detailed appearance and shape of vehicles are visible in these images. These methods often build an explicit appearance model [3][4][5] for vehicle extraction. However, satellite images have relatively lower resolution compared with aerial images; thus, an explicit appearance-based model [3][4][5] is not appropriate for satellite images.…”

Section: Introductionmentioning

confidence: 99%

Moving Vehicle Information Extraction from Single-Pass WorldView-2 Imagery Based on ERGAS-SNS Analysis

Gao

et al. 2014

Remote Sensing

View full text Add to dashboard Cite

Due to the fact that WorldView-2 (WV2) has a small time lag while acquiring images from panchromatic (PAN) and two multispectral (MS1 and MS2) sensors, a moving vehicle is located at different positions in three image bands. Consequently, such displacement can be utilized to identify moving vehicles, and vehicle information, such as speed and direction can be estimated. In this paper, we focus on moving vehicle detection according to the displacement information and present a novel processing chain. The vehicle locations are extracted by an improved morphological detector based on the vehicle's shape properties. To make better use of the time lag between MS1 and MS2, a band selection process is performed by both visual inspection and quantitative analysis. Moreover, three spectral-neighbor band pairs, which have a major contribution to vehicle identification, are selected. In addition, we improve the spatial and spectral analysis method by incorporating local ERGAS index analysis (ERGAS-SNS) to identify moving vehicles. The experimental results on WV2 images showed that the correctness, completeness and quality rates of the proposed method were about 94%, 91% and 86%, respectively. Thus, the proposed method has good performance for moving vehicle detection and information extraction.

show abstract

“…Such kind of data can be used for applications, such as automatic traffic monitoring, border surveillance, or protection of critical infrastructures. In this article, we will focus on video data acquired with a frame rate of 25 Hz by a small UAV in top-down view at an altitude of 400 m. The ground coverage is up to 0.5 km 2 with a ground sampling distance (GSD) of about 0.3 m∕pixel. Such parameters are usual for so-called full-motion video (FMV) sequences.…”

Section: Introductionmentioning

confidence: 99%

Moving object detection in top-view aerial videos improved by image stacking

2017

View full text Add to dashboard Cite

Abstract. Image stacking is a well-known method that is used to improve the quality of images in video data. A set of consecutive images is aligned by applying image registration and warping. In the resulting image stack, each pixel has redundant information about its intensity value. This redundant information can be used to suppress image noise, resharpen blurry images, or even enhance the spatial image resolution as done in superresolution. Small moving objects in the videos usually get blurred or distorted by image stacking and thus need to be handled explicitly. We use image stacking in an innovative way: image registration is applied to small moving objects only, and image warping blurs the stationary background that surrounds the moving objects. Our video data are coming from a small fixed-wing unmanned aerial vehicle (UAV) that acquires top-view gray-value images of urban scenes. Moving objects are mainly cars but also other vehicles such as motorcycles. The resulting images, after applying our proposed image stacking approach, are used to improve baseline algorithms for vehicle detection and segmentation. We improve precision and recall by up to 0.011, which corresponds to a reduction of the number of false positive and false negative detections by more than 3 per second. Furthermore, we show how our proposed image stacking approach can be implemented efficiently. © The Authors. Published by SPIE under a Creative Commons Attribution 3.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

show abstract

A Novel Vehicle Detection Method With High Resolution Highway Aerial Image

Cited by 70 publications

References 19 publications

Arbitrary-Oriented Vehicle Detection in Aerial Imagery with Single Convolutional Neural Networks

Arbitrary-Oriented Vehicle Detection in Aerial Imagery with Single Convolutional Neural Networks

Moving Vehicle Information Extraction from Single-Pass WorldView-2 Imagery Based on ERGAS-SNS Analysis

Moving object detection in top-view aerial videos improved by image stacking

Contact Info

Product

Resources

About