Moving Object Detection Research Articles

Detection of Moving Object Using Superpixel Fusion Network

Moving object detection is still a challenging task in complex scenes. The existing methods based on deep learning mainly use U-Nets and have achieved amazing results. However, they ignore the local continuity between pixels. In order to solve this problem, a method based on a superpixel fusion network (SF-Net) is proposed in this article. First, the median filter is used to extract the candidate foreground (called pixel features ) and the image sequence is segmented by superpixel. Then, the histogram features (called superpixel features ) of the candidate foreground superpixels are extracted. Next, the pixel features and the superpixel features are the inputs of SF-Net, respectively. Experiments show the effectiveness of SF-Net on 34 image sequences and the average F-measure reaches 0.84. SF-Net can remove more background noise and has stronger expression ability than a network with the same depth.

Design and implementation of moving object detection based on Zynq

In recent years, video image processing technology has made rapid progress. Some algorithms related to moving target detection and tracking, relying on the rich resources of computers, make the implementation of these algorithms based on the PC platform has been relatively mature, but there are problems such as poor real-time performance, high power consumption, resource consumption. The Zynq hardware platform has both FPGA, which is good at parallel operation, and ARM core, which is good at control, which can effectively implement the algorithm transplantation of moving target detection and effectively improve the above shortcomings. The system takes Zynq hardware platform as the core unit, which is composed of video image acquisition module, image processing module, information transmission module, DDR cache module and display module. The PL side of Zynq implements video image acquisition, gray conversion, frame difference algorithm, expansion corrosion algorithm. The PS terminal mainly completes the configuration of IIC camera and VDMA. The output module finally realizes the output of HDMI through protocol conversion. This system has wide application value in moving target detection.

A Hybrid Approach for Moving Object Detection Using TV-L1 Features and RPCA–MOG

A Hybrid Approach for Moving Object Detection Using TV-L1 Features and RPCA–MOG

Robot Programming from a Single Demonstration for High Precision Industrial Insertion

We propose a novel approach for robotic industrial insertion tasks using the Programming by Demonstration technique. Our method allows robots to learn a high-precision task by observing human demonstration once, without requiring any prior knowledge of the object. We introduce an Imitated-to-Finetuned approach that generates imitated approach trajectories by cloning the human hand's movements and then fine-tunes the goal position with a visual servoing approach. To identify features on the object used in visual servoing, we model object tracking as the moving object detection problem, separating each demonstration video frame into the moving foreground that includes the object and demonstrator's hand and the static background. Then a hand keypoints estimation function is used to remove the redundant features on the hand. The experiment shows that the proposed method can make robots learn precision industrial insertion tasks from a single human demonstration.

A robust RGB‐D visual odometry with moving object detection in dynamic indoor scenes

AbstractSimultaneous localisation and mapping (SLAM) are the basis for many robotic applications. As the front end of SLAM, visual odometry is mainly used to estimate camera pose. In dynamic scenes, classical methods are deteriorated by dynamic objects and cannot achieve satisfactory results. In order to improve the robustness of visual odometry in dynamic scenes, this paper proposed a dynamic region detection method based on RGB‐D images. Firstly, all feature points on the RGB image are classified as dynamic and static using a triangle constraint and the epipolar geometric constraint successively. Meanwhile, the depth image is clustered using the K‐Means method. The classified feature points are mapped to the clustered depth image, and a dynamic or static label is assigned to each cluster according to the number of dynamic feature points. Subsequently, a dynamic region mask for the RGB image is generated based on the dynamic clusters in the depth image, and the feature points covered by the mask are all removed. The remaining static feature points are applied to estimate the camera pose. Finally, some experimental results are provided to demonstrate the feasibility and performance.

A computationally efficient moving object detection technique using tensor QR decomposition based TRPCA framework

Advancements in high-quality video cameras and the consequent capture of minute details of the scene have led the field of computer vision to remarkable heights. This paper develops a tensor QR decomposition-based approach for Moving Object Detection (MOD), which aims to reduce the computational complexity without disturbing the structural framework of the input video frames. The increased performance and efficiency of the proposed method lie in the usage of tensor QR decomposition along with l2,1 norm and l1/2 norm. It is designed on top of a tensor-based Robust Principal Component Analysis (TRPCA) framework. In addition, this work safeguards the variation along the spatio-temporal directions with the effective use of Tensor Total Variation (TTV) regularization. The results and the analysis prove that the proposed method improves the F-measure by 15%–45% and reduces the computational complexity by 75%–85% with respect to the counterparts.

Convolutional Neural Networks for Object Detection and Recognition

One of the essential technologies in the fields of target extraction, pattern recognition, and motion measurement is moving object detection. Finding moving objects or a number of moving objects across a series of frames is called object tracking. Basically, object tracking is a difficult task. Unexpected changes in the surroundings, an item's mobility, noise, etc., might make it difficult to follow an object. Different tracking methods have been developed to solve these issues. This paper discusses a number of object tracking and detection approaches. The major methods for identifying objects in images will be discussed in this paper. Recent years have seen impressive advancements in fields like pattern recognition and machine learning, both of which use convolutional neural networks (CNNs). It is mostly caused by graphics processing units'(GPUs) enhanced parallel processing capacity. This article describes many kinds of object classification, object racking, and object detection techniques. Our results showed that the suggested algorithm can detect moving objects reliably and efficiently in a variety of situations.

Research Progress on the Human Behavior Recognition Based on Machine Learning Methods

Background: Machine vision has been used in the industrial automation system for a long time. It also plays a significant role in the field of human behavior recognition. Behavior recognition based on machine vision, such as object tracking, motion detection and crime recognition, greatly broadens the application field of artificial intelligence and has a good application prospect. Objective: We summarize the latest applications of various machine learning algorithms in human behavior recognition, and analyze the accuracy of various algorithms combined with data sets, so as to provide reference for researchers in related fields. Methods: By sorting out the typical research results, briefly expound on the application of machine learning in the field of behavior recognition in recent years. This review focuses on the Two Stream Network structure, TSN structure, LSTM network and C3D network. Results: This paper analyzes the principles, advantages and disadvantages of various human behavior recognition methods, and briefly discusses the future development direction. Conclusion: The wide application prospect of behavior recognition and detection makes it a hot research direction in the field of computer vision, and greatly improves the accuracy of complex human motion recognition combined with deep learning. However, it still faces many difficulties, such as insufficient discrimination of violence attributes, difficult collection, verification of special action data and insufficient hardware computing resources, etc.

Moving object detection method with motion regions tracking in background subtraction

Moving object detection method with motion regions tracking in background subtraction

An Efficient Low Complexity Region-of-Interest Detection for Video Coding in Wireless Visual Surveillance

Following its use in several applications, including video coding in wireless surveillance, moving object detection (MOD) has become a popular video analysis topic. Despite the considerable progress in the accuracy of MOD for video coding, its implementation in constrained sensors is a real challenge owing to their high complexity and energy consumption. Therefore, there is a great need to address the trade-off between the accuracy and the energy efficiency of MOD approaches for video coding in constrained systems. In this work, an energy-efficient region-of-interest (ROI) detection algorithm as a pre-encoder for wireless visual surveillance (WVS) is proposed. The algorithm ensures a trade-off between detection accuracy and computational complexity. To this end, we propose constructing an activity map by measuring each block activity between successive frames. The map scores are processed using a combination of a fast Gaussian smoother and a rank-order filter to improve accuracy. Only the blocks in motion are coded and counted for transmission. The accuracy of our approach has been evaluated on a large dataset using key performance metrics. It has been found that our algorithm outperforms other state-of-the-art techniques in terms of true positive rate (TPR), with 80.84% on sensitivity metric, while exhibiting a well-balanced accuracy for all categories. A careful examination of the computational complexity confirms the low overhead. The energy and bitrate savings could achieve nearly 90% and 98%, respectively.

Hyper RPCA: Joint Maximum Correntropy Criterion and Laplacian Scale Mixture Modeling on-the-Fly for Moving Object Detection

Moving object detection is critical for automated video analysis in many vision-related tasks, such as surveillance tracking, video compression coding, etc. Robust Principal Component Analysis (RPCA), as one of the most popular moving object modelling methods, aims to separate the temporally-varying (i.e., moving) foreground objects from the static background in video, assuming the background frames to be low-rank while the foreground to be spatially sparse. Classic RPCA imposes sparsity of the foreground component using <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\ell _1$</tex-math></inline-formula> -norm, and minimizes the modeling error via <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\ell _2$</tex-math></inline-formula> -norm. We show that such assumptions can be too restrictive in practice, which limits the effectiveness of the classic RPCA, especially when processing videos with dynamic background, camera jitter, camouflaged moving object, etc. In this paper, we propose a novel RPCA-based model, called Hyper RPCA, to detect moving objects on the fly. Different from classic RPCA, the proposed Hyper RPCA jointly applies the maximum correntropy criterion (MCC) for the modeling error, and Laplacian scale mixture (LSM) model for foreground objects. Extensive experiments have been conducted, and the results demonstrate that the proposed Hyper RPCA has competitive performance for foreground detection to the state-of-the-art algorithms on several well-known benchmark datasets.

A Visual Target Representation using Saliency Detection Approach

The task of saliency detection is to identify the most important and informative part of a scene. Saliency detection is broadly applied to numerous vision problems, including image segmentation, object recognition, image compression, content-based image retrieval, and moving object detection. Existing saliency detection methods suffer a low accuracy rate because of missing components of saliency regions. This study proposes a visual saliency detection method for the target representation to represent targets more accurately. The proposed method consists of five modules. In the first module, the salient region is extracted through manifold ranking on a graph, which incorporates local grouping cues and boundary priors. Secondly, using a region of interest (ROI) algorithm and the subtraction of the salient region from the original image, other parts of the image, either related or nonrelated to the interested target, are segmented. Lastly, those related and non-related regions are classified and distinguished using our proposed algorithm. Experimental result shows that proposed salient region accurately represent the interested target which can be used for object detection and tracking applications.

Moving object detection for surveillance video frames using two stage multi-scale residual convolution neural networks

Moving object detection for surveillance video frames using two stage multi-scale residual convolution neural networks

Retracted: Optimization Algorithm of Moving Object Detection Using Multiscale Pyramid Convolutional Neural Networks.

[This retracts the article DOI: 10.1155/2023/3320547.].

SMod: Scene-Specific-Prior–Based Moving Object Detection for Airport Apron Surveillance Systems

The detection of moving objects in airport apron surveillance encounters serious detection defects, which reflects that the classification is biased toward the background. In this article, we propose a new method, scene-specific-prior–based moving object detection (SMod), to detect the moving object by the use of the prior knowledge specific to the airport apron. We find that the airport apron is made of concrete and has a special gray–white color distribution. Therefore, first, we use a dual-mode Gaussian distribution to fit the color distribution of the airport apron. Further analysis shows that this fitted distribution also reflects the probability of a detection defect, which occurs when the aircraft and occluded apron area share a similar color distribution. Based on this, second, we present a scene-specific prior model based on the dual-mode distribution, where pixels with a larger detection defect probability are more likely to be classified as the foreground, so that the prior model is able to bias the classification to the foreground. As a result, the detection defect in the airport apron can be compensated for. Third, the prior model is used in conjunction with an apron model and an object model to detect a moving object within a Bayesian framework. Next, we conduct comparison experiments on the airport ground video surveillance benchmark to verify the effectiveness of the proposed algorithm. Finally, we demonstrate the application of SMod in an airport apron surveillance system.

Research on Moving Object Detection based on Camshift Algorithm and Kalman Filter

The key content of video image processing and analysis is the detection and tracking of moving objects, and it is also the focus and important research field of computer vision. It has important applications in unmanned operation, defense industry, human-computer interaction, image processing and other fields. In this paper, under the development environment of Spyder and Opencv, the autonomous adaptability of Camshift tracking algorithm is combined with kalman filter algorithm, so the moving target detection and tracking in video monitoring is realized by using python language.

The Autonomous Train vision: Embedded AI for pedestrians monitoring

When you develop a perception system for rolling stocks of the railway sector, you are dealing with huge infrastructures and harsh conditions never encountered. From the integration studies to the final software implementation of the computer vision algorithm in the embedded system, our work puts on paper these steps and challenges encountered by focusing on one specific use-case of the environment monitoring of a train: pedestrians tracking in front of the train. Pedestrian monitoring is a key aspect of autonomous train operation as it involves ensuring the safety of people in the vicinity of the tracks. This scenario covers most of the requirements for automatic detection scenarios at the front of a train: close and distant moving object detection, robust object tracking, person state analysis with high confidence rates to ensure safety for human life and for train driving.

Moving Object Detection Based on Nonconvex Rank Approximation and Three-Dimensional Total Variation

Moving Object Detection Based on Nonconvex Rank Approximation and Three-Dimensional Total Variation

Motion Robust High-Speed Light-Weighted Object Detection With Event Camera

The event camera asynchronously produces the event stream with a high temporal resolution, discarding redundant visual information and bringing new possibilities for moving object detection. Nevertheless, the existing object detectors cannot make the most of the spatial-temporal asynchronous nature and high temporal resolution of the event stream. For one thing, existing methods fail to consider objects with different velocities relative to the event camera’s motion, resulting from the global synchronized time window with the whole spatial slice. For another, most of the existing methods rely on heavy models and boost the detection performance with low frame rates, failing to utilize the high temporal resolution characteristic of the event stream. In this work, we propose a motion robust and high-speed detection pipeline which better leverages the event data. First, we design an event stream representation called Temporal Active Focus (TAF), which efficiently utilizes the spatial-temporal asynchronous event stream, constructing event tensors robust to object motions. Then, we propose a module called the Bifurcated Folding Module (BFM), which encodes the rich temporal information in the TAF tensor at the input layer of the detector. Following this, we design a high-speed lightweight detector called Agile Event Detector (AED) plus a simple but effective data augmentation method, to enhance the detection accuracy and reduce the model’s parameter. Experiments on two typical real-scene event camera object detection datasets show that our method is competitive in terms of accuracy, efficiency, and the number of parameters. By classifying objects into multiple motion levels based on the optical flow density metric, we further illustrated the robustness of our method for objects with different velocities relative to the camera. The codes and trained models are available at https://github.com/HarmoniaLeo/FRLW-EvD.

Incorporating Deep Background Prior Into Model-Based Method for Unsupervised Moving Vehicle Detection in Satellite Videos

Background reconstruction is a key step of moving object detection in satellite videos. Most existing model-based methods exploit low-rank prior to recover background, which have achieved good performance but suffered degradation under complex and dynamic scenes. In this paper, we introduce a deep background prior into model-based methods for moving vehicle detection in satellite videos. Our deep background prior is obtained by a background reconstruction network, which can learn to reconstruct background from consecutive frames. By applying our deep background prior into model-based methods, a closed-form solution can be obtained via alternating direction method of multipliers (ADMM) and then detection results can be acquired through iterative optimization. More importantly, our background reconstruction network can be trained in an unsupervised way by introducing specifically designed loss, thus relieving the dependence on large-scale labeled dataset. Extensive experimental results demonstrate the efficiency and effectiveness of the proposed method.