Dynamic Object Detection Research Articles

Efficiency analysis of dynamic object detection in computer vision system

The concept of computer vision and its key aspects are given. Problems of dynamic objects detection are considered. The latest approaches are described to improve the accuracy and speed of recognition. Their main advantages and disadvantages are considered. The structure of the computer vision system and the interaction of its components are shown. A method for embedding a motion detection module to increase the efficiency of the recognition subsystem is proposed. A motion vector search algorithm is described, the main idea of which is to divide a frame into blocks and search for similar parts in adjacent frames. Experimental results showing the effectiveness of the approach are demonstrated.

DynaSLAM: Tracking, Mapping, and Inpainting in Dynamic Scenes

The assumption of scene rigidity is typical in SLAM algorithms. Such a strong assumption limits the use of most visual SLAM systems in populated real-world environments, which are the target of several relevant applications like service robotics or autonomous vehicles. In this paper we present DynaSLAM, a visual SLAM system that, building over ORB-SLAM2 [1], adds the capabilities of dynamic object detection and background inpainting. DynaSLAM is robust in dynamic scenarios for monocular, stereo and RGB-D configurations. We are capable of detecting the moving objects either by multi-view geometry, deep learning or both. Having a static map of the scene allows inpainting the frame background that has been occluded by such dynamic objects. We evaluate our system in public monocular, stereo and RGB-D datasets. We study the impact of several accuracy/speed trade-offs to assess the limits of the proposed methodology. DynaSLAM outperforms the accuracy of standard visual SLAM baselines in highly dynamic scenarios. And it also estimates a map of the static parts of the scene, which is a must for long-term applications in real-world environments.

A Study on Improvement of Dynamic Object Detection using Dense Grid Model and Anchor Model

A Study on Improvement of Dynamic Object Detection using Dense Grid Model and Anchor Model

Patch-based detection of dynamic objects in CrowdCam images

A scene can be divided into two parts: static and dynamic. The parts of the scene which do not admit any motion are static regions, while moving objects correspond to dynamic regions. In this work, we tackle the challenging task of identifying dynamic objects present in the CrowdCam images. Our approach exploits the coherency present in the natural images and utilizes the epipolar geometry present between a pair of images to achieve this objective. It does not require a dynamic object to be present in all the given images. We show that the proposed approach obtains state-of-the-art accuracy on standard datasets.

Hazardous Object Detection by Using Kinect Sensor in a Handle-Type Electric Wheelchair.

To ensure the safety of a handle-type electric wheelchair (hereinafter, electric wheelchair), this paper describes the applicability of using a Kinect sensor. Ensuring the mobility of elderly people is a particularly important issue to be resolved. An electric wheelchair is useful as a means of transportation for elderly people. Considering that the users of electric wheelchairs are elderly people, it is important to ensure the safety of electric wheelchairs at night. To ensure the safety of an electric wheelchair at night, we constructed a hazardous object detection system using commercially available and inexpensive Kinect sensors and examined the applicability of the system. We examined warning timing with consideration to the cognition, judgment, and operation time of elderly people. Based on this, a hazardous object detection area was determined. Furthermore, the detection of static and dynamic hazardous objects was carried out at night and the results showed that the system was able to detect with high accuracy. We also conducted experiments related to dynamic hazardous object detection during daytime. From the above, it showed that the system could be applicable to ensuring the safety of the handle-type electric wheelchair.

Self-Adapting Fuzzy Model for Dynamic Object Detection Using RGB-D Information

This paper describes a novel method for dynamic object detection in RGB-D videos based completely on a fuzzy logic approach. The method is an original contribution because of its self-adapting fuzzy scheme that fuses color and depth information (RGB-D). The fuzzy system analyzes information related to fuzzy color and depth differences as well as fuzzy depth similitude. In order to improve the segmentation results, special cases for incomplete information in the depth pixels are treated by four new fuzzy pixel concepts; complete pixels, empty pixel, new pixel, and color pixel. The fuzzy method also solves flickering and oscillations on edge depth measurements. The proposed system also involves a self-adapting background update mechanism to avoid problems regarding changes in the video scenario sequence, and manual parameter adjustment required in other reported methods. Although the proposed method is self-adapting, it has a better or similar performance in most of the comparative cases used for analysis.

Optical flow based system for detection of dynamic objects for uavs

This work presents an optical flow based method for obstacle detection by using a single CCDcamera. Computed optical flow is used to detect dynamic obstacles in front of the camera and toadjust rotor's control to avoid them. The proposed system is based on optical flow estimation with weighted image blocks from the streamed video. Hardware simulation is performed to prove theapplicability of this system. Methods and algorithms described in this paper are versatile enough andcan be implemented for various vehicles with autonomous navigation system. The feasibility of theproposed system for UAVs is discussed

The detection algorithm of irregular dynamic objects

Using remote sensing data for marine monitoring, marine rescue, marine pollution monitoring which has a broad monitoring area and fast response time, so in the last 10 years, satellite borne or airborne optical and SAR sensor data have been increasingly used in the field of ocean monitoring. However, based on the dynamic video to carry out the study of the detection of irregular debris blocks from the wrecked ship, aircraft is less. To a great extent, it affects the efficiency of maritime rescue. This paper, based on the dynamic objects detection, Color Space Quantization and property of Human Vision System, takes the irregular wreckage patches as research. And a detection algorithm for dynamic objects is developed with the foundation of Lab channels. To verify that, the calculation of the Euclidean distance between the characteristic parameters of irregular wreckage patches and regular floating ones, and the average Euclidean distance is 0.8245 between the irregular1 and the regular while that between irregular2 and the regular is 4.3645. At the same time, the Hausdorff distance was calculated and verified, and the average distance between the irregular block 1 and the regular block was 2.5975. The average distance between the block 2 and the rule block was 13.8962. Experimental results show that the method is consistent with the results of the second methods, which proves that the first method is scientific and operational. Therefore, it can be found that some parameters including divergence, elongation and eccentricity fluctuate dramatically from those in irregular ones to the regular one, which could be extracted to recognize or distinguish the patches. That is why this paper is of importance in marine rescue and detection of objects on the sea surface.

Automated Detection, Locking and Hitting a Fast Moving Aerial Object by Image Processing (Suitable For Guided Missile)

Due to passive tracking, fire and forget capabilities and ease of operation of guided missiles have emerged as an important anti-aircraft arsenal. Detection of target in real time is a difficult task when object is dynamic and even harder when the object tends to move at speed counted in Mach numbers. Moving target detection is a key area in image processing, infusion of this technology to the purpose of tracking target and destroying as in guided missiles can be very effective as it will reduce network links, and GPS navigation in aggressive electronic warfare environments. Detecting moving objects in real-time is a challenging problem due to the computational limits and the motions of the camera. In this paper, we suggest a method for dynamic object detection and tracking on non-stationary cameras running within few milliseconds (ms) on a PC, and real-time on mobile devices. Detecting of object by background subtraction method does not give better results when object is moving very fast, object is very tiny and presence of lighting effect. In order to overcome these troubles, we propose a new method for Moving object Detection in Dynamic Background along with the development of a guided missile using the process. It achieves dynamic landscape using certain possibility of time and subsequent frame difference method and addresses the difficult scenario, where object is moving very fast and background changes frequently. The experimental results show that the proposed method can detect moving object more efficiently and completely in both cases online as well as offline video. The results indicate that the proposed algorithm outperforms the majority of earlier state-of-the-art algorithms not only in terms of accuracy, but also in terms of processing speed.

Automatic wavelet-based segmentation of a background-and-target frame from an optoelectronic device for detection of dynamic objects in 2D images

We propose an invariant adaptive technique for automated segmentation of a target-and-background frame from an optoelectronic device for detection of dynamic objects in the image. The technique involves performing a wavelet transform on the image such that threshold processing of wavelet coefficients is optimum (in the sense of the Neyman–Pearson principle) based on a very powerful local unbiased test, and does not require any a priori data on the target environment, any reference images of the dynamic objects, or the locations and dimensions of the windows used for object detection. This is implemented solely using the information contained in images recorded by the optoelectronic device. We present an algorithm and results from an assessment of segmentation quality statistics for non-steady-state (and steady-state) images under various operating conditions. The technique described in this paper is found to be highly efficient and can be implemented as a real-time algorithm.

Fuzzy-neural self-adapting background modeling with automatic motion analysis for dynamic object detection

In this paper we propose a system that involves a Background Subtraction, BS, model implemented in a neural Self Organized Map with a Fuzzy Automatic Threshold Update that is robust to illumination changes and slight shadow problems. The system incorporates a scene analysis scheme to automatically update the Learning Rates values of the BS model considering three possible scene situations. In order to improve the identification of dynamic objects, an Optical Flow algorithm analyzes the dynamic regions detected by the BS model, whose identification was not complete because of camouflage issues, and it defines the complete object based on similar velocities and direction probabilities. These regions are then used as the input needed by a Matte algorithm that will improve the definition of the dynamic object by minimizing a cost function. Among the original contributions of this work are; an adapting fuzzy-neural segmentation model whose thresholds and learning rates are adapted automatically according to the changes in the video sequence and the automatic improvement on the segmentation results based on the Matte algorithm and Optical flow analysis. Findings demonstrate that the proposed system produces a competitive performance compared with state-of-the-art reported models by using BMC and Li databases.

Model-free detection and tracking of dynamic objects with 2D lidar

We present a new approach to detection and tracking of moving objects with a 2D laser scanner for autonomous driving applications. Objects are modelled with a set of rigidly attached sample points along their boundaries whose positions are initialized with and updated by raw laser measurements, thus allowing a non-parametric representation that is capable of representing objects independent of their classes and shapes. Detection and tracking of such object models are handled in a theoretically principled manner as a Bayes filter where the motion states and shape information of all objects are represented as a part of a joint state which includes in addition the pose of the sensor and geometry of the static part of the world. We derive the prediction and observation models for the evolution of the joint state, and describe how the knowledge of the static local background helps in identifying dynamic objects from static ones in a principled and straightforward way. Dealing with raw laser points poses a significant challenge to data association. We propose a hierarchical approach, and present a new variant of the well-known Joint Compatibility Branch and Bound algorithm to respect and take advantage of the constraints of the problem introduced through correlations between observations. Finally, we calibrate the system systematically on real world data containing 7,500 labelled object examples and validate on 6,000 test cases. We demonstrate its performance over an existing industry standard targeted at the same problem domain as well as a classical approach to model-free object tracking.

Self-adaptive SOM-CNN neural system for dynamic object detection in normal and complex scenarios

This paper proposes a novel bio-inspired neural system based on Self-organizing Maps (SOMs) and Cellular Neural Networks (CNNs), called SOM-CNN, to detect dynamic objects in normal and complex scenarios. A contribution of our work is a Retinotopic SOM (RESOM) architecture feasible for video and motion analysis. It is inspired by the visual perception mechanism of the human visual cortex, and satisfactorily addresses the disadvantages encountered by other methods in the area. We also propose a new CNN scheme for image thresholding, called Neighbor Threshold CNN (NTCNN), and a self-adapting parameter scheme for the RESOM and the NTCNN models. The proposed system can deal with sudden and gradual illumination changes, dynamic backgrounds, camouflage, camera jitter, and stopped dynamic objects. Experimental results on complex scenarios, using the Precision (Pe), Recall (Rc), F measure, (F1) and Similarity (Si) metrics, yield acceptable average performances with Pe=0.875, Rc=0.8316, F1=0.843 and Si=0.741. Results also show that our proposed system performs better than other methods that have been suggested in the literature. The system can process information at 35fps, rendering it suitable for real-time applications.

An Adaptive Unsupervised Neural Network Based on Perceptual Mechanism for Dynamic Object Detection in Videos with Real Scenarios

The analysis of moving objects in video sequences has been a paramount issue in applications related to intelligent surveillance systems, robotics, and medicine. Although several works aimed to analyze objects in video sequences have been reported, many of them need manual parameter adjustments and they are not tolerant to illumination changes and dynamic backgrounds. Therefore, a novel scheme termed Dynamic Retinotopic SOM based on an adaptive artificial neural network, to detect moving objects is proposed in this work. The neural network is a model based on the mechanisms of the visual cortex that we called Retinotopic SOM (RESOM) and it is also proposed in this paper. Furthermore, RESOM is a real-time neural network that can adapt its learning parameters based on the scene behavior and it mimics perception abilities. A quantitative comparison with other segmentation methods reported in the literature using real video scenes showed that the proposed DR-SOM segmentation method automatically adjusts its parameters and outperforms the reported methods in condition of dynamic backgrounds, and gradual and sudden illumination changes.

Detection and Tracking of Dynamic Objects by Using a Multirobot System: Application to Critical Infrastructures Surveillance

The detection and tracking of mobile objects (DATMO) is progressively gaining importance for security and surveillance applications. This article proposes a set of new algorithms and procedures for detecting and tracking mobile objects by robots that work collaboratively as part of a multirobot system. These surveillance algorithms are conceived of to work with data provided by long distance range sensors and are intended for highly reliable object detection in wide outdoor environments. Contrary to most common approaches, in which detection and tracking are done by an integrated procedure, the approach proposed here relies on a modular structure, in which detection and tracking are carried out independently, and the latter might accept input data from different detection algorithms. Two movement detection algorithms have been developed for the detection of dynamic objects by using both static and/or mobile robots. The solution to the overall problem is based on the use of a Kalman filter to predict the next state of each tracked object. Additionally, new tracking algorithms capable of combining dynamic objects lists coming from either one or various sources complete the solution. The complementary performance of the separated modular structure for detection and identification is evaluated and, finally, a selection of test examples discussed.

Detection of dynamic objects on the basis of space-time anomalies in video sequences

Codes and algorithms are developed for detecting small-size dynamic thermal objects on the basis of searching for space-time anomalies in the observation field formed by a sequence of infrared images. Results of studying the method effectiveness, based on data obtained under conditions of a real background-target environment, are presented.

Detection of small-size dynamic objects by a moving observation system

The use of the algorithm of real-time determination of local displacements of fragments (blocks) with due allowance for spatial and temporal coupling of motion is proposed for estimating the background component during detecting small-size dynamic objects (in the case of unknown motion of the observation system). The efficiency of this method is compared with that of the methods based on affine transformations of the image as a whole. It is demonstrated that this method is more efficient and ensures background suppression in the difference frame under the condition that it is presented by large zones deforming or displacing relative to each other.

Dynamic objects detection through visual odometry and stereo-vision: a study of inaccuracy and improvement sources

Road safety, whatever the considered environment, relies heavily on the ability to detect and track moving objects from a moving point of view. In order to achieve such a detection, the vehicle's ego-motion must first be estimated and compensated. This issue is crucial to complete a fully autonomous vehicle; this is why several approaches have already been proposed. This study presents a method, based solely on visual information that implements such a process. Information from stereo-vision and motion is derived to extract the vehicle's ego-motion. Ego-motion extraction algorithm is thoroughly evaluated in terms of precision and uncertainty. Given those statistical attributes, a method for dynamic objects detection is presented. This method relies on 3D image registration and residual displacement field evaluation. This method is then evaluated on several real and synthetic data sequences. It will be shown that it allows a reliable and early detection, even in hard cases (e.g. occlusions,...). Given a few additional factors (detectable motion range), overall performances can be derived from visual odometry performances.

Research on Mobile Robot SLAM in Dynamic Environment

A SLAMiDE（SLAM in Dynamic Environments) system is designed and realized in the paper, which supplies a holistic framework and a series of implementation methods for mobile robot SLAM in dynamic environments. A uniform target model is proposed in SLAMiDE system. The dynamic targets and static targets and the mobile robot pose are estimated simultaneously, by synthesized the research of the data association and dynamic targets detection and static SLAM based on local maps. Finally, the results of the experimental test prove that the SLAMiDE system can realize dynamic objects detection and mapping and location correctly.

Detection, Tracking and Avoidance of Multiple Dynamic Objects

Real-time motion planning in an unknown environment involves collision avoidance of static as well as moving agents. Strategies suitable for navigation in a stationary environment cannot be translated as strategies per se for dynamic environments. In a purely stationary environment all that the sensor can detect can only be a static object is assumed implicitly. In a mixed environment such an assumption is no longer valid. For efficient collision avoidance identification of the attribute of the detected object as static or dynamic is probably inevitable. Presented here are two novel schemes for perceiving the presence of dynamic objects in the robot's neighborhood. One of them, called the Model-Based Approach (MBA) detects motion by observing changes in the features of the environment represented on a map. The other CBA (cluster-based approach) partitions the contents of the environment into clusters representative of the objects. Inspecting the characteristics of the partitioned clusters reveals the presence of dynamic agents. The extracted dynamic objects are tracked in consequent samples of the environment through a straightforward nearest neighbor rule based on the Euclidean metric. A distributed fuzzy controller avoids the tracked dynamic objects through direction and velocity control of the mobile robot. The collision avoidance scheme is extended to overcome multiple dynamic objects through a priority based averaging technique (PBA). Indicating the need for additional rules apart from the PBA to overcome conflicting decisions while tackling multiple dynamic objects can be considered as another contribution of this effort. The method has been tested through simulations by navigating a sensor-based mobile robot amidst multiple dynamic objects and its efficacy established.