Object Detection In Video Sequences Research Articles

Video Global Motion Compensation Based on Affine Inverse Transform Model.

Global motion greatly increases the number of false alarms for object detection in video sequences against dynamic backgrounds. Therefore, before detecting the target in the dynamic background, it is necessary to estimate and compensate the global motion to eliminate the influence of the global motion. In this paper, we use the SURF (speeded up robust features) algorithm combined with the MSAC (M-Estimate Sample Consensus) algorithm to process the video. The global motion of a video sequence is estimated according to the feature point matching pairs of adjacent frames of the video sequence and the global motion parameters of the video sequence under the dynamic background. On this basis, we propose an inverse transformation model of affine transformation, which acts on each adjacent frame of the video sequence in turn. The model compensates the global motion, and outputs a video sequence after global motion compensation from a specific view for object detection. Experimental results show that the algorithm proposed in this paper can accurately perform motion compensation on video sequences containing complex global motion, and the compensated video sequences achieve higher peak signal-to-noise ratio and better visual effects.

AN IMPROVED MOVING OBJECTS DETECTION ALGORITHM IN VIDEO SEQUENCES

Context. The implementation of video analytics functions in video surveillance systems makes it possible to increase the efficiency of these systems. One of the functions of these intelligent video surveillance systems is to detect dynamic objects in the surveillance sectors of video surveillance cameras. Existing methods of background subtractoin and object recognition have important disadvantages that limit their application in practice: under low contrast algorithms can not select an object from the background; some moving objects can be recognized as a background, algorithms critical to lighting conditions, and so on. Therefore, an important task is to develop and improve methods for detecting dynamic objects in video sequences.Objective. The research is devoted to the development of an improved method for detecting dynamic objects in video sequences.Method. For moving objects detection in video sequences we used background subtraction methods based on pixel-by-pixel analysis of frames using elements of the expert systems theory.Results. In this paper, we propose an improved method for detecting dynamic objects in video sequences, which is based on the ViBe algorithm. The proposed approach differs from original the using of U*V*W* color model, using double threshold levels and some elements of theory expert systems for removal of vaguenesses in pixel classification (Dempster-Shafer theory) and dynamic method for updating background pixel models. Proposed algorithm include following stages: initialization of the background model (for each pixel with known parameters, the number of previous values in the current frame is stored); foreground detection; the next step is a calculation amounts of points, that belong to the foreground and to the background. For removal of vaguenesses in pixel classification we used some elements of Dempster-Shafer theory. After initialization of the background model and foreground detection next stage is updating background model. For this we used a three-level constructed neighborhood of the studied pixel and used of the even distribution of random values is into each of three levels.Conclusions. Experimental research of the improved algorithm in comparing to original ViBe conducted with the use of test frames from a set of CDNET in the various variants of environment and with the different variants of discriminability. The consolidated results specify on the improvement of results of an offer method as compared to original ViBe on the average on 6,7%.

Fusing Self-Organized Neural Network and Keypoint Clustering for Localized Real-Time Background Subtraction.

Moving object detection in video streams plays a key role in many computer vision applications. In particular, separation between background and foreground items represents a main prerequisite to carry out more complex tasks, such as object classification, vehicle tracking, and person re-identification. Despite the progress made in recent years, a main challenge of moving object detection still regards the management of dynamic aspects, including bootstrapping and illumination changes. In addition, the recent widespread of Pan-Tilt-Zoom (PTZ) cameras has made the management of these aspects even more complex in terms of performance due to their mixed movements (i.e. pan, tilt, and zoom). In this paper, a combined keypoint clustering and neural background subtraction method, based on Self-Organized Neural Network (SONN), for real-time moving object detection in video sequences acquired by PTZ cameras is proposed. Initially, the method performs a spatio-temporal tracking of the sets of moving keypoints to recognize the foreground areas and to establish the background. Then, it adopts a neural background subtraction, localized in these areas, to accomplish a foreground detection able to manage bootstrapping and gradual illumination changes. Experimental results on three well-known public datasets, and comparisons with different key works of the current literature, show the efficiency of the proposed method in terms of modeling and background subtraction.

Analysis and Trends on Moving Object Detection Algorithm Techniques

This paper presents a survey on dynamic object detection in video sequences. Many methods have been proposed during several years that intent to solve the problems of dynamic background, jittering, illumination changes, camouflage, among other. The survey is intended to provide a recent analysis of these methods to highlight the main characteristics of each approach. The survey is based on published paper from 2013 up to date. 77 methods were found, and they are described and analyzed in this survey. In addition, the survey proposes a complete classification of the methods based on the type of technique used to achieve the detection of dynamic objects. It also evaluates the limitations of each approach and the tendencies regarding the most used techniques, color space, datasets, hardware, programming language and processing time. One of the most popular approaches correspond to advanced statistical models, and artificial neural networks with 28% and 22% respectively. The analysis reports 11% of use of GPUs, most of them found in the neural network approaches. Regarding datasets, there are authors that report the use of three datasets the most popular is Change Detection. The most used software to implement the methods is MATLAB and the RGB color space, the most employed.

Spatio-Temporal Closed-Loop Object Detection

Object detection is one of the most important tasks of computer vision. It is usually performed by evaluating a subset of the possible locations of an image, that are more likely to contain the object of interest. Exhaustive approaches have now been superseded by object proposal methods. The interplay of detectors and proposal algorithms has not been fully analyzed and exploited up to now, although this is a very relevant problem for object detection in video sequences. We propose to connect, in a closed-loop, detectors and object proposal generator functions exploiting the ordered and continuous nature of video sequences. Different from tracking we only require a previous frame to improve both proposal and detection: no prediction based on local motion is performed, thus avoiding tracking errors. We obtain three to four points of improvement in mAP and a detection time that is lower than Faster Regions with CNN features (R-CNN), which is the fastest Convolutional Neural Network (CNN) based generic object detector known at the moment.

Moving Object Segmentation in a Video Sequence using Optical Flow and Motion Histogram Technique

The moving object detection and tracking in video sequence is significant research area in the field of computer vision and image processing. Object detection and tracking is key step for object recognition, navigation systems and surveillance systems. An effort has been made to develop an approach for moving object detection in video sequence, based on motion segmentation using optical flow and motion histogram. The algorithm has been described in detail and its competence was checked by performing simulation experiments. ROC comparison shows that this algorithm gives better result than traditional methods.

Object detection in video sequences by a temporal modular self-adaptive SOM

A video segmentation algorithm that takes advantage of using a background subtraction (BS) model with low learning rate (LLR) or a BS model with high learning rate (HLR) depending on the video scene dynamics is presented in this paper. These BS models are based on a neural network architecture, the self-organized map (SOM), and the algorithm is termed temporal modular self-adaptive SOM, TMSA_SOM. Depending on the type of scenario, the TMSA_SOM automatically classifies and processes each video into one of four different specialized modules based on an initial sequence analysis. This approach is convenient because unlike state-of-the-art (SoA) models, our proposed model solves different situations that may occur in the video scene (severe dynamic background, initial frames with dynamic objects, static background, stationary objects, etc.) with a specialized module. Furthermore, TMSA_SOM automatically identifies whether the scene has drastically changed (e.g., stationary objects of interest become dynamic or drastic illumination changes have occurred) and automatically detects when the scene has become stable again and uses this information to update the background model in a fast way. The proposed model was validated with three different video databases: Change Detection, BMC, and Wallflower. Findings showed a very competitive performance considering metrics commonly used in the literature to compare SoA models. TMSA_SOM also achieved the best results on two perceptual metrics, Ssim and D-Score, and obtained the best performance on the global quality measure, FSD (based on F-Measure, Ssim, and D-Score), demonstrating its robustness with different and complicated non-controlled scenarios. TMSA_SOM was also compared against SoA neural network approaches obtaining the best average performance on Re, Pr, and F-Measure.

AN A-CONTRARIO APPROACH FOR OBJECT DETECTION IN VIDEO SEQUENCE

This study focuses on the problem of object detection in video sequences. In order to free from the modeling of the objects that may be variable and numerous, we choose an a-contrario approach, based on the modeling of the absence of any object of interest in the scene (noise model) and the images are analyzed in order to detect the events salient relative to the used noise model. To free from the a-priori parameters, we define a non-monotonic measure that is a Number of False Alarms (NFA) and that allows quantifying the 'exceptional' feature of an observation relatively to the noise model. With such an approach the solution is determined as the argument minimizing the NFA criterion. Considering an image segmentation problem, the proposed noise model has two, namely pixel and window, levels in order to take into account both ra- diometric and spatial noise feature. The same algorithm is then used to detect either the changes relative to a background, or in the case of an embedded cam- era, the objects having their own motion, or the objects protruding relatively to the road plane, so that applications are related to video surveillance and Advanced Driver Assistance Systems.