- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Background-Foreground Interaction for Moving Object Detection in Dynamic Scenes
摘要： Both background subtraction and foreground extraction are the typical methods used to detect moving objects in video sequences. In order to flexibly represent the long-term state and the short-term changes in a scene, a new weighted Kernel Density Estimation (KDE) is proposed to build the long-term background (LTB) and short-term foreground (STF) models, respectively. A novel mechanism is proposed to support the interaction between the LTB and STF models. The interaction includes the weight transmission and the fusion between the LTB and STF models. In the weight transmission process between the LTB and STF models, the sample weight of one model (either the background model or the foreground model) in the current time step is updated under the guidance of the decision of the other model in the previous time step. In the background-foreground fusion stage, a unified Bayesian framework is proposed to detect objects and the detection result in any time step is given by the logarithm of the posterior ratio between the background and foreground models. This interactive approach proposed in this paper improves the robustness of moving object detection, preventing deadlocks and degeneration in the models. The experimental results demonstrate that our proposed approach outperforms previous ones.
关键词： Weighted kernel density estimation,Background-foreground interaction,Moving object detection,Dynamic scene
更新于2025-09-23 15:23:52
-
[IEEE 2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV) - Singapore, Singapore (2018.11.18-2018.11.21)] 2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV) - Downside Hemisphere Object Detection and Localization of MAV by Fisheye Camera
摘要： For a multirotor micro aerial vehicle (MAV) flying in the outdoor environment, its downside hemisphere has richest visual information. All that information can be obtained by a single fisheye camera with larger than 180 degrees field of view (FOV). Traditionally, the unrestored fisheye image is restored to a flat image before subsequent processing, which is both resource and time consuming. In this paper, to save resource and time, a method of fisheye object detection and localization on the unrestored fisheye image is proposed. A single-stage neural network is built for object detection. To improve the performance of detector, its submodules are designed specifically by combining the central rotational property and severe distortion of the fisheye image. To meet the real-time requirements of onboard computation, the detector is also tuned to be light-weight. After that, the detected objects are localized with assistance of by a data fusion on the fisheye model and MAV sensory data (altitude, attitude, etc.). The experimental results have validated the effectiveness of the proposed methods in this paper.
关键词： deep learning,object detection,data fusion
更新于2025-09-23 15:23:52
-
[IEEE 2018 Ubiquitous Positioning, Indoor Navigation and Location-Based Services (UPINLBS) - Wuhan (2018.3.22-2018.3.23)] 2018 Ubiquitous Positioning, Indoor Navigation and Location-Based Services (UPINLBS) - Image Processing Based Indoor Localization System for Assisting Visually Impaired People
摘要： Indoor localization or indoor positioning system is a known as a process of detecting position of any object or people inside a building or room by different sensory data collected from different devices using different techniques such as radio waves, magnetic fields, acoustic signals or other procedures. However, lacking of a standard localization system is still a very big concern. Solution of this issue can be very beneficial for people in many cases but it can be especially very beneficial for the visually impaired people. In this paper, an image processing based indoor localization system has been developed using OpenCV and Python by following color detection technique to detect position of the user with maximum accuracy and then location of user is determined by analyzing that location matrix. Location accuracy depends on the size of the matrix and successful identification of target color. Firebase real time database was added to the system which made real time operations between server and the user end device easier. To justify the proposed model, successful experiments were conducted in indoor environments as well and correct result was achieved each time by detecting accurate locations. This will be very advantageous to observe the fully or partially sightless people and guide them towards their destination and also to inspect them for their security purpose.
关键词： Color Segmentation,Indoor localization,Image Processing,Indoor positioning system,Wireless communication,Connected object detection
更新于2025-09-23 15:23:52
-
Class Agnostic Image Common Object Detection
摘要： Learning similarity of two images is an important problem in computer vision and has many potential applications. Most of previous works focus on generating image similarities in three aspects: global feature distance computing, local feature matching and image concepts comparison. However, the task of directly detecting class agnostic common objects from two images has not been studied before, which goes one step further to capture image similarities at region level. In this paper, we propose an end-to-end Image Common Object Detection Network (CODN) to detect class agnostic common objects from two images. The proposed method consists of two main modules: locating module and matching module. The locating module generates candidate proposals of each two images. The matching module learns the similarities of the candidate proposal pairs from two images, and re?nes the bounding boxes of the candidate proposals. The learning procedure of CODN is implemented in an integrated way and a multi-task loss is designed to guarantee both region localization and common object matching. Experiments are conducted on PASCAL VOC 2007 and COCO 2014 datasets. Experimental results validate the effectiveness of the proposed method.
关键词： Common object detection,relation network,siamese network
更新于2025-09-23 15:22:29
-
Detection of Multiclass Objects in Optical Remote Sensing Images
摘要： Object detection in complex optical remote sensing images is a challenging problem due to the wide variety of scales, densities, and shapes of object instances on the earth surface. In this letter, we focus on the wide-scale variation problem of multiclass object detection and propose an effective object detection framework in remote sensing images based on YOLOv2. To make the model adaptable to multiscale object detection, we design a network that concatenates feature maps from layers of different depths and adopt a feature introducing strategy based on oriented response dilated convolution. Through this strategy, the performance for small-scale object detection is improved without losing the performance for large-scale object detection. Compared to YOLOv2, the performance of the proposed framework tested in the DOTA (a large-scale data set for object detection in aerial images) data set improves by 4.4% mean average precision without adding extra parameters. The proposed framework achieves real-time detection for 1024 ×1024 image using Titan Xp GPU acceleration.
关键词： Feature introducing strategy,optical remote sensing image,object detection,oriented response (OR) dilated convolution
更新于2025-09-23 15:22:29
-
Color–depth multi-task learning for object detection in haze
摘要： Haze environments pose serious challenges for object detection, making existing methods difficult to generate satisfied results. However, there is no escape from haze environments in real-world applications, especially in water and bad weather. Hence, it is necessary to enable object detection methods to conquer the difficulties caused by the haze effect. In spite of the diversity between various conditions, haze environments share a common characteristic that the haze concentration is changed with the scene depth. Hence, this haze concentration feature can be used as a representation of the scene depth. This provides us a novel cue available for object detection in haze that the object-background depth contrast can be identified. In this paper, we propose a multi-task learning-based object detection method by jointly using the color and depth features. A pair of background models is built separately with the color and depth features, forming two streams of our multi-task learning framework. The final object detection results are generated by fusing the results given by color and depth features. In contrast to existing object detection methods, the novelty of our method lies in the combination of the color and depth features under a unified multi-task learning mechanism, which is experimentally demonstrated to be robust against challenging haze environments.
关键词： Multi-task learning,Haze environment,Depth feature,Object detection
更新于2025-09-23 15:22:29
-
A Sample Update-Based Convolutional Neural Network Framework for Object Detection in Large-Area Remote Sensing Images
摘要： This letter addresses the issue of accurate object detection in large-area remote sensing images. Although many convolutional neural network (CNN)-based object detection models can achieve high accuracy in small image patches, the models perform poorly in large-area images due to the large quantity of false and missing detections that arise from complex backgrounds and diverse groundcover types. To address this challenge, this letter proposes a sample update-based CNN (SUCNN) framework for object detection in large-area remote sensing images. The proposed framework contains two stages. In the first stage, a base model—single-shot multibox detector—is trained with the training data set. In the second stage, artificial composite samples are generated to update the training set. The parameters of the first-stage model are fine-tuned with the updated data set to obtain the second-stage model. The first- and second-stage models are evaluated using the large-area remote sensing image test set. Comparison experiments show the effectiveness and superiority of the proposed SUCNN framework for object detection in large-area remote sensing images.
关键词： large-area remote sensing images,sample update,object detection,Convolutional neural networks (CNNs)
更新于2025-09-23 15:22:29
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Inshore Ship Detection in Sar Images Based on Deep Neural Networks
摘要： Inshore ship detection in SAR image faces difficulties on correctly identifying near-shore ships and onshore objects. This article proposes a multi-scale full convolutional network (MS-FCN) based sea-land segmentation method and applies a rotatable bounding box based object detection method (DR-Box) to solve the inshore ship detection problem. The sea region and land region are separated by MS-FCN then DR-Box is applied on sea region. The proposed method combines global information and local information of SAR image to achieve high accuracy. The networks are trained with Chinese Gaofen-3 satellite images. Experiments on the testing image show most inshore ships are successfully located by the proposed method.
关键词： object detection networks,full convolutional networks,deep learning,inshore ship detection,Synthetic aperture radar
更新于2025-09-23 15:21:21
-
[IEEE 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) - Chongqing (2018.6.27-2018.6.29)] 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) - Morphology-Based Visual Detection of Foreign Object on Overhead Line Tower
摘要： The interfering objects often hang on the overhead line with a large number, which brings great inconvenience and hurdles to the inspection and repair for maintainers. In the field of Unmanned Aerial Vehicle (UAV) routing inspection, many scholars focus on how to detect foreign object on images of power equipment. This paper proposes to use the combination of the morphological closing operation and morphological features restriction to give an accurate detection of the location and quantity of foreign object pictured by the UAV. experiments show that the accuracy is greater than 95%.There is no denying that human costs can be slashed, and at the same time, enhance the inspection and repair capabilities of maintenance personnel.
关键词： morphological features,foreign object detection,overhead line tower,closing operation
更新于2025-09-23 15:21:21
-
Multiscale Visual Attention Networks for Object Detection in VHR Remote Sensing Images
摘要： Object detection plays an active role in remote sensing applications. Recently, deep convolutional neural network models have been applied to automatically extract features, generate region proposals, and predict corresponding object class. However, these models face new challenges in VHR remote sensing images due to the orientation and scale variations and the cluttered background. In this letter, we propose an end-to-end multiscale visual attention networks (MS-VANs) method. We use skip-connected encoder–decoder model to extract multiscale features from a full-size image. For feature maps in each scale, we learn a visual attention network, which is followed by a classification branch and a regression branch, so as to highlight the features from object region and suppress the cluttered background. We train the MS-VANs model by a hybrid loss function which is a weighted sum of attention loss, classification loss, and regression loss. Experiments on a combined data set consisting of Dataset for Object Detection in Aerial Images and NWPU VHR-10 show that the proposed method outperforms several state-of-the-art approaches.
关键词： object detection,VHR remote sensing image,visual attention,Multiscale feature
更新于2025-09-23 15:21:21