DETECTION OF CITIES VEHICLE FLEET USING YOLO V2 AND AERIAL IMAGES

<p><strong>Abstract.</strong> Recent progress in deep learning methods has shown that key steps in object detection and recognition can be performed with convolutional neural networks (CNN). In this article, we adapt YOLO (You Only Look Once) to a new approach to perform object detection on satellite imagery. This system uses a single convolutional neural network (CNN) to predict classes and bounding boxes. The network looks at the entire image at the time of the training and testing, which greatly enhances the differentiation of the background since the network encodes the essential information for each object. The high speed of this system combined with its ability to detect and classify multiple objects in the same image makes it a compelling argument for use with satellite imagery.</p>

Download Full-text

Object Detection Based on Global-Local Saliency Constraint in Aerial Images

Remote Sensing ◽

10.3390/rs12091435 ◽

2020 ◽

Vol 12 (9) ◽

pp. 1435 ◽

Cited By ~ 1

Author(s):

Chengyuan Li ◽

Bin Luo ◽

Hailong Hong ◽

Xin Su ◽

Yajun Wang ◽

...

Keyword(s):

Object Detection ◽

Semantic Information ◽

Feature Fusion ◽

Aerial Images ◽

Natural Image ◽

Optical Remote Sensing ◽

Complex Background ◽

Bounding Boxes ◽

The Impact ◽

Oriented Bounding Boxes

Different from object detection in natural image, optical remote sensing object detection is a challenging task, due to the diverse meteorological conditions, complex background, varied orientations, scale variations, etc. In this paper, to address this issue, we propose a novel object detection network (the global-local saliency constraint network, GLS-Net) that can make full use of the global semantic information and achieve more accurate oriented bounding boxes. More precisely, to improve the quality of the region proposals and bounding boxes, we first propose a saliency pyramid which combines a saliency algorithm with a feature pyramid network, to reduce the impact of complex background. Based on the saliency pyramid, we then propose a global attention module branch to enhance the semantic connection between the target and the global scenario. A fast feature fusion strategy is also used to combine the local object information based on the saliency pyramid with the global semantic information optimized by the attention mechanism. Finally, we use an angle-sensitive intersection over union (IoU) method to obtain a more accurate five-parameter representation of the oriented bounding boxes. Experiments with a publicly available object detection dataset for aerial images demonstrate that the proposed GLS-Net achieves a state-of-the-art detection performance.

Download Full-text

EFN: Field-Based Object Detection for Aerial Images

Remote Sensing ◽

10.3390/rs12213630 ◽

2020 ◽

Vol 12 (21) ◽

pp. 3630

Author(s):

Jin Liu ◽

Haokun Zheng

Keyword(s):

Object Detection ◽

Semantic Segmentation ◽

Natural Images ◽

Aerial Images ◽

Aerial Image ◽

Data Sets ◽

Data Set ◽

Bounding Box ◽

Good Score ◽

Bounding Boxes

Object detection and recognition in aerial and remote sensing images has become a hot topic in the field of computer vision in recent years. As these images are usually taken from a bird’s-eye view, the targets often have different shapes and are densely arranged. Therefore, using an oriented bounding box to mark the target is a mainstream choice. However, this general method is designed based on horizontal box annotation, while the improved method for detecting an oriented bounding box has a high computational complexity. In this paper, we propose a method called ellipse field network (EFN) to organically integrate semantic segmentation and object detection. It predicts the probability distribution of the target and obtains accurate oriented bounding boxes through a post-processing step. We tested our method on the HRSC2016 and DOTA data sets, achieving mAP values of 0.863 and 0.701, respectively. At the same time, we also tested the performance of EFN on natural images and obtained a mAP of 84.7 in the VOC2012 data set. These extensive experiments demonstrate that EFN can achieve state-of-the-art results in aerial image tests and can obtain a good score when considering natural images.

Download Full-text

GLE-Net: A Global and Local Ensemble Network for Aerial Object Detection

International Journal of Computational Intelligence Systems ◽

10.1007/s44196-021-00056-3 ◽

2022 ◽

Vol 15 (1) ◽

Author(s):

Jiajia Liao ◽

Yujun Liu ◽

Yingchao Piao ◽

Jinhe Su ◽

Guorong Cai ◽

...

Keyword(s):

Deep Learning ◽

Object Detection ◽

Aerial Images ◽

Visual Object ◽

Detection Algorithms ◽

Integration Strategy ◽

Bounding Boxes ◽

Global And Local ◽

Deep Learning Model

AbstractRecent advances in camera-equipped drone applications increased the demand for visual object detection algorithms with deep learning for aerial images. There are several limitations in accuracy for a single deep learning model. Inspired by ensemble learning can significantly improve the generalization ability of the model in the machine learning field, we introduce a novel integration strategy to combine the inference results of two different methods without non-maximum suppression. In this paper, a global and local ensemble network (GLE-Net) was proposed to increase the quality of predictions by considering the global weights for different models and adjusting the local weights for bounding boxes. Specifically, the global module assigns different weights to models. In the local module, we group the bounding boxes that corresponding to the same object as a cluster. Each cluster generates a final predict box and assigns the highest score in the cluster as the score of the final predict box. Experiments on benchmarks VisDrone2019 show promising performance of GLE-Net compared with the baseline network.

Download Full-text

Segmentation based rotated bounding boxes prediction and image synthesizing for object detection of high resolution aerial images

Neurocomputing ◽

10.1016/j.neucom.2020.01.039 ◽

2020 ◽

Vol 388 ◽

pp. 202-211 ◽

Cited By ~ 1

Author(s):

Yingming Wang ◽

Lijun Wang ◽

Huchuan Lu ◽

You He

Keyword(s):

High Resolution ◽

Object Detection ◽

Aerial Images ◽

Bounding Boxes

Download Full-text

Multi-Scale Feature Integrated Attention-Based Rotation Network for Object Detection in VHR Aerial Images

Sensors ◽

10.3390/s20061686 ◽

2020 ◽

Vol 20 (6) ◽

pp. 1686 ◽

Cited By ~ 3

Author(s):

Feng Yang ◽

Wentong Li ◽

Haiwei Hu ◽

Wanyi Li ◽

Peng Wang

Keyword(s):

Object Detection ◽

Large Scale ◽

Ground Truth ◽

Classification Performance ◽

Aerial Images ◽

Detection Methods ◽

Robust Detection ◽

Scale Feature ◽

Multi Scale ◽

Bounding Boxes

Accurate and robust detection of multi-class objects in very high resolution (VHR) aerial images has been playing a significant role in many real-world applications. The traditional detection methods have made remarkable progresses with horizontal bounding boxes (HBBs) due to CNNs. However, HBB detection methods still exhibit limitations including the missed detection and the redundant detection regions, especially for densely-distributed and strip-like objects. Besides, large scale variations and diverse background also bring in many challenges. Aiming to address these problems, an effective region-based object detection framework named Multi-scale Feature Integration Attention Rotation Network (MFIAR-Net) is proposed for aerial images with oriented bounding boxes (OBBs), which promotes the integration of the inherent multi-scale pyramid features to generate a discriminative feature map. Meanwhile, the double-path feature attention network supervised by the mask information of ground truth is introduced to guide the network to focus on object regions and suppress the irrelevant noise. To boost the rotation regression and classification performance, we present a robust Rotation Detection Network, which can generate efficient OBB representation. Extensive experiments and comprehensive evaluations on two publicly available datasets demonstrate the effectiveness of the proposed framework.

Download Full-text

New Approach for Object Detection and Extraction from Digital Images for Providing a 3D Model Applicable in 3D GIS

Architecture and Design ◽

10.4018/978-1-5225-7314-2.ch050 ◽

2019 ◽

pp. 1324-1349

Author(s):

Amir Saeed Homainejad

Keyword(s):

Object Detection ◽

Point Cloud ◽

3D Model ◽

Aerial Images ◽

Aerial Image ◽

Point Cloud Data ◽

3D Gis ◽

New Approach ◽

Cloud Data ◽

3D Space

This paper discusses a new approach in object extraction from aerial images with association of point cloud data. The extracted objects are captured in a 3D space for reconstructing a 3D model. The process includes three steps. In the first step the targeted objects are extracted from point cloud data and captured in a 3D space. The objects include buildings, trees, roads and background or terrain. In the second step the extracted objects are registered to the aerial image for assisting the object detection. Finally, the extracted objects from the aerial image are registered on the original 3D model for conversion to the point cloud data and then are captured in a 3D space for reconstructing a new 3D model. The final 3D model is flexible and editable. The objects can be edited, audited, and manipulated without affecting another objects or ruin the 3D model. Also, more data can be integrated in the 3D model improve its quality. The aspects of this project are: to reconstruct the final 3D model, and then each object can be interactively updated or modified without affecting the whole 3D model, and to provide a database for other users such as 3D GIS, city management and planning, Disaster Management System (DBS), and Smart City application.

Download Full-text

Mask OBB: A Semantic Attention-Based Mask Oriented Bounding Box Representation for Multi-Category Object Detection in Aerial Images

Remote Sensing ◽

10.3390/rs11242930 ◽

2019 ◽

Vol 11 (24) ◽

pp. 2930 ◽

Cited By ~ 6

Author(s):

Jinwang Wang ◽

Jian Ding ◽

Haowen Guo ◽

Wensheng Cheng ◽

Ting Pan ◽

...

Keyword(s):

Object Detection ◽

Empirical Studies ◽

Classification Problem ◽

Aerial Images ◽

Detection Methods ◽

Detection Accuracy ◽

Lateral Connection ◽

Feature Pyramid ◽

Bounding Boxes ◽

Definition Of

Object detection in aerial images is a fundamental yet challenging task in remote sensing field. As most objects in aerial images are in arbitrary orientations, oriented bounding boxes (OBBs) have a great superiority compared with traditional horizontal bounding boxes (HBBs). However, the regression-based OBB detection methods always suffer from ambiguity in the definition of learning targets, which will decrease the detection accuracy. In this paper, we provide a comprehensive analysis of OBB representations and cast the OBB regression as a pixel-level classification problem, which can largely eliminate the ambiguity. The predicted masks are subsequently used to generate OBBs. To handle huge scale changes of objects in aerial images, an Inception Lateral Connection Network (ILCN) is utilized to enhance the Feature Pyramid Network (FPN). Furthermore, a Semantic Attention Network (SAN) is adopted to provide the semantic feature, which can help distinguish the object of interest from the cluttered background effectively. Empirical studies show that the entire method is simple yet efficient. Experimental results on two widely used datasets, i.e., DOTA and HRSC2016, demonstrate that the proposed method outperforms state-of-the-art methods.

Download Full-text

Yaw Galloping of a TLWP Platform Under High Speed Currents by Analytical Methods and its Comparison With Experimental Results

Volume 1: Offshore Technology ◽

10.1115/omae2017-61909 ◽

2017 ◽

Author(s):

Francisco Lamas ◽

Miguel A. M. Ramirez ◽

Antonio Carlos Fernandes

Keyword(s):

High Speed ◽

Production Systems ◽

Experimental Tests ◽

Experimental Results ◽

Analytical Methodology ◽

New Approach ◽

Laboratory Facilities ◽

Polynomial Curve ◽

Computational Fluid Dynamics Cfd ◽

Cfd Analyses

Flow Induced Motions are always an important subject during both design and operational phases of an offshore platform life. These motions could significantly affect the performance of the platform, including its mooring and oil production systems. These kind of analyses are performed using basically two different approaches: experimental tests with reduced models and, more recently, with Computational Fluid Dynamics (CFD) dynamic analysis. The main objective of this work is to present a new approach, based on an analytical methodology using static CFD analyses to estimate the response on yaw motions of a Tension Leg Wellhead Platform on one of the several types of motions that can be classified as flow-induced motions, known as galloping. The first step is to review the equations that govern the yaw motions of an ocean platform when subjected to currents from different angles of attack. The yaw moment coefficients will be obtained using CFD steady-state analysis, on which the yaw moments will be calculated for several angles of attack, placed around the central angle where the analysis is being carried out. Having the force coefficients plotted against the angle values, we can adjust a polynomial curve around each analysis point in order to evaluate the amplitude of the yaw motion using a limit cycle approach. Other properties of the system which are flow-dependent, such as damping and added mass, will also be estimated using CFD. The last part of this work consists in comparing the analytical results with experimental results obtained at the LOC/COPPE-UFRJ laboratory facilities.

Download Full-text