Pedestrian Tracking Method Research Articles

CCBA-NMS-YD: A Vehicle Pedestrian Detection and Tracking Method Based on Improved YOLOv7 and DeepSort

In this paper, we propose a vehicle pedestrian detection and tracking method based on the improved YOLOv7 and DeepSort algorithms. We aim to improve the quality of vehicle pedestrian detection and tracking, addressing the challenges that current commercially available autonomous driving technologies face in complex and changing road traffic situations. First, the NMS (non-maximum suppression) algorithm in YOLOv7 is replaced with a modified Soft-NMS algorithm to ensure that targets can be accurately detected at high densities, and second, the CCBA (coordinate channel attention module) attention mechanism is incorporated to improve the feature extraction and perception capabilities of the network. Finally, a multi-scale feature network is introduced to extract features of small targets more accurately. Finally, the MobileNetV3 lightweight module is introduced into the feature extraction network of DeepSort, which not only reduces the number of model parameters and network complexity, but also improves the tracking performance of the target. The experimental results show that the improved YOLOv7 algorithm improves the average detection accuracy by 3.77% compared to that of the original algorithm; on the MOT20 dataset, the refined DeepSort model achieves a 1.6% increase in MOTA and a 1.9% improvement in MOTP; in addition, the model volume is one-eighth of the original algorithm. In summary, our model is able to achieve the desired real-time and accuracy, which is more suitable for autonomous driving.

Pedestrian tracking method based on S-YOFEO framework in complex scene

A real-time stable multi-target tracking method based on the enhanced You Only Look Once-v8 (YOLOv8) and the optimized Simple Online and Realtime Tracking with a Deep association metric (DeepSORT) for multi-target tracking (S-YOFEO) is proposed with the aim of addressing the issue of target ID transformation and loss caused by the increase of practical background complexity. For the purpose of further enhancing the representation of small-scale features, a small target detection head is first introduced to the detection layer of YOLOv8 in this paper with the aim of collecting more detailed information by increasing the detection resolution of YOLOv8. Secondly, the Omni-Scale Network (OSNet) feature extraction network is implemented to enable accurate and efficient fusion of the extracted complex and comparable feature information, taking into account the restricted computational power of DeepSORT’s original feature extraction network. Again, a novel adaptive forgetting Kalman filter algorithm (FSA) is devised to enhance the precision of model prediction and the effectiveness of parameter updates to adjust to the uncertain movement speed and trajectory of pedestrians in real scenarios. Following that, an accurate and stable association matching process is obtained by substituting Efficient-Intersection over Union (EIOU) for Complete-Intersection over Union (CIOU) in DeepSORT to boost the convergence speed and matching effect during association matching. Last but not least, One-Shot Aggregation (OSA) is presented as the trajectory feature extractor to deal with the various noise interferences in the complex scene. OSA is highly sensitive to information of different scales, and its one-time aggregation property substantially decreases the computational overhead of the model. According to the trial results, S-YOFEO has made some developments as its precision can reach 78.2% and its speed can reach 56.0 frames per second (FPS).

Enhancing Pedestrian Tracking in Autonomous Vehicles by Using Advanced Deep Learning Techniques

Effective collision risk reduction in autonomous vehicles relies on robust and straightforward pedestrian tracking. Challenges posed by occlusion and switching scenarios significantly impede the reliability of pedestrian tracking. In the current study, we strive to enhance the reliability and also the efficacy of pedestrian tracking in complex scenarios. Particularly, we introduce a new pedestrian tracking algorithm that leverages both the YOLOv8 (You Only Look Once) object detector technique and the StrongSORT algorithm, which is an advanced deep learning multi-object tracking (MOT) method. Our findings demonstrate that StrongSORT, an enhanced version of the DeepSORT MOT algorithm, substantially improves tracking accuracy through meticulous hyperparameter tuning. Overall, the experimental results reveal that the proposed algorithm is an effective and efficient method for pedestrian tracking, particularly in complex scenarios encountered in the MOT16 and MOT17 datasets. The combined use of Yolov8 and StrongSORT contributes to enhanced tracking results, emphasizing the synergistic relationship between detection and tracking modules.

Multi-objective pedestrian tracking method based on YOLOv8 and improved DeepSORT.

A multi-objective pedestrian tracking method based on you only look once-v8 (YOLOv8) and the improved simple online and real time tracking with a deep association metric (DeepSORT) was proposed with the purpose of coping with the issues of local occlusion and ID dynamic transformation that frequently arise when tracking target pedestrians in real complex traffic scenarios. To begin with, in order to enhance the feature extraction network's capacity to learn target feature information in busy traffic situations, the detector implemented the YOLOv8 method with a high level of small-scale feature expression. In addition, the omni-scale network (OSNet) feature extraction network was then put on top of DeepSORT in order to accomplish real-time synchronized target tracking. This increases the effectiveness of picture edge recognition by dynamically fusing the collected feature information at various scales. Furthermore, a new adaptive forgetting smoothing Kalman filtering algorithm (FSA) was created to adapt to the nonlinear condition of the pedestrian trajectory in the traffic scene in order to address the issue of poor prediction attributed to the linear state equation of Kalman filtering once more. Afterward, the original intersection over union (IOU) association matching algorithm of DeepSORT was replaced by the complete-intersection over union (CIOU) association matching algorithm to fundamentally reduce the target pedestrians' omission and misdetection situation and to improve the accuracy of data matching. Eventually, the generalized trajectory feature extractor model (GFModel) was developed to tightly merge the local and global information through the average pooling operation in order to get precise tracking results and further decrease the impact of numerous disturbances on target tracking. The fusion algorithm of YOLOv8 and improved DeepSORT method based on OSNet, FSA and GFModel was named YOFGD. According to the experimental findings, YOFGD's ultimate accuracy can reach 77.9% and its speed can reach 55.8 frames per second (FPS), which is more than enough to fulfill the demands of real-world scenarios.

A cross-camera pedestrian trajectory tracking method in shopping mall environment

Pedestrian trajectory in the shopping mall environment plays an important role in criminal investigation, passenger flow statistics, big data recommendation and many other fields. In this paper, a pedestrian trajectory tracking method is proposed, which is based on artificial intelligence algorithms. The method is composed of three modules. First, YoloX is applied to detect pedestrians; secondly, the BYTE algorithm is applied to track pedestrians; finally, the FastReID network and matching algorithms are applied to identify pedestrians. In addition, we also use the BrainFrame platform to package and deploy the algorithm. Experiments show that this method can effectively perform person re-identification tasks with low performance requirements, thus contribute to pedestrian trajectory tracking task in shopping mall environment.

Siam Deep Feature KCF Method and Experimental Study for Pedestrian Tracking.

The tracking of a particular pedestrian is an important issue in computer vision to guarantee societal safety. Due to the limited computing performances of unmanned aerial vehicle (UAV) systems, the Correlation Filter (CF) algorithm has been widely used to perform the task of tracking. However, it has a fixed template size and cannot effectively solve the occlusion problem. Thus, a tracking-by-detection framework was designed in the current research. A lightweight YOLOv3-based (You Only Look Once version 3) mode which had Efficient Channel Attention (ECA) was integrated into the CF algorithm to provide deep features. In addition, a lightweight Siamese CNN with Cross Stage Partial (CSP) provided the representations of features learned from massive face images, allowing the target similarity in data association to be guaranteed. As a result, a Deep Feature Kernelized Correlation Filters method coupled with Siamese-CSP(Siam-DFKCF) was established to increase the tracking robustness. From the experimental results, it can be concluded that the anti-occlusion and re-tracking performance of the proposed method was increased. The tracking accuracy Distance Precision (DP) and Overlap Precision (OP) had been increased to 0.934 and 0.909 respectively in our test data.

PTZ Active Vision Method Based On BEBLID

The traditional pan-tilt-zoom (PTZ) camera relies on manual operation in control, and it requires a large number of samples for training in the algorithm to achieve higher target recognition accuracy. Therefore, we introduce the Boosted Efficient Binary Local Image Descriptor (BEBLID) propose a pedestrian detection and tracking method applied to the PTZ. By extracting image feature points and feature descriptions, we use Support Vector Machines (SVM) to train fewer samples to complete pedestrian detection. Then we input it into kernel correlation filters (KCF) for subsequent tracking, and use its high frame rate to reduce the feedback steps of the PTZ position loop, which reduces the system running time, and then we control the target image to be always locked in the center of the image. Finally, the experiment is carried out, and the whole system can run normally. Under 700 test samples, the detection effect of this algorithm is the highest, reaching 93.00 %, which is 14.57 % and 3.57 % higher than that of Scale-invariant feature transform (SIFT) and Oriented Brief (ORB).

Multi-object pedestrian tracking method based on improved high resolution neural network

Multi-object pedestrian tracking method based on improved high resolution neural network

Stable and real-time pedestrian tracking method based on improved DeepSORT under complex background

Stable and real-time pedestrian tracking method based on improved DeepSORT under complex background

Research on Pedestrian Detection and DeepSort Tracking in Front of Intelligent Vehicle Based on Deep Learning

In order to improve the tracking failure caused by small-target pedestrians and partially blocked pedestrians in dense crowds in complex environments, a pedestrian target detection and tracking method for an intelligent vehicle was proposed based on deep learning. On the basis of the YOLO detection model, the channel attention module and spatial attention module were introduced and were joined to the back of the backbone network Darknet-53 in order to achieve weight amplification of important feature information in channel and space dimensions and improve the representation ability of the model for important feature information. Based on the improved YOLO network, the flow of the DeepSort pedestrian tracking method was designed and the Kalman filter algorithm was used to estimate the pedestrian motion state. The Mahalanobis distance and apparent feature were used to calculate the similarity between the detection frame and the predicted pedestrian trajectory; the Hungarian algorithm was used to achieve the optimal matching of pedestrian targets. Finally, the improved YOLO pedestrian detection model and the DeepSort pedestrian tracking method were verified in the same experimental environment. The verification results showed that the improved model can improve the detection accuracy of small-target pedestrians, effectively deal with the problem of target occlusion, reduce the rate of missed detection and false detection of pedestrian targets, and improve the tracking failure caused by occlusion.

Pedestrian multi-target tracking method based on YOLOv5 and person re-identification

Pedestrian multi-target tracking method based on YOLOv5 and person re-identification

A Pedestrian Detection and Tracking Method for Robot Equipped with Laser Radar

In order to detect and track pedestrians in complex indoor backgrounds, a pedestrian detection and tracking method for indoor robots equipped with Laser radar is proposed. Firstly, The SLAM (Simultaneous Location and Mapping) technology is applied to obtain 2D grid map for a strange environment; then, Monte Carlo localization is employed to obtain the posterior pose of the robot in the map; then, an improved likelihood field background subtraction algorithm is proposed to extract the interesting foreground in changeable environment; then, the hierarchical clustering algorithm combining with an improved leg model is proposed to detect the objective pedestrian; at last, an improved tracking intensity formula is designed to track and follow the objective pedestrian. Experimental results in some complex environments show that our method can effectively reduce the impact of confusing scenarios which are challenges for other algorithms, such as the motion of the chair, the suddenly passing by person and when the objective pedestrian close to the wall and so on, and can detect, track and follow pedestrians in real time with high accuracy.

A Pedestrian Tracking Method Based on Adaboost and Feature Fusion

In view of the existing time-consuming and identity exchange problems in the pedestrian tracking process. A multi feature fusion tracking method based on adaboost detection is proposed. Firstly, the multi-scale wavelet transform is used to extract the foreground regions of the moving target, and the Haar-like feature is used in the foreground region to detect human heads. Then the particle filter tracking algorithm is introduced by combining color and gradient direction histogram to track the detected heads. Finally, the pedestrians are tracked through the association matrix. The experimental results show that the proposed method has a good tracking result when there are the cross motion and short occlusion between the pedestrians.

A fast particle filter pedestrian tracking method based on colour, texture and corresponding space information

In order to track pedestrians accurately, a fast particle filter pedestrian tracking method based on colour, texture and corresponding space information is proposed. In this algorithm, firstly, we extract space information of object pedestrian and disintegrate it into three local regions. In addition, employ the improved texture and colour information extract algorithm to get the joint texture and colour information from the corresponding sub-region. Finally, determine the position of object by colour-texture similarity indicator based on space division, and get the result of accurately track. In consideration of the multi thread information fusion algorithm need a larger number of particles, this factor could reduce the computational efficiency. Therefore, a wave integral histogram algorithm is proposed for improving arithmetic speed. The experiment carried out on videos, result indicates the effectiveness and efficiency of the proposed method, which can achieve higher accuracy than other tow state of the art algorithms in the actual traffic scene, and the real-time performance also has been improved considerably.

A fast particle filter pedestrian tracking method based on colour, texture and corresponding space information

In order to track pedestrians accurately, a fast particle filter pedestrian tracking method based on colour, texture and corresponding space information is proposed. In this algorithm, firstly, we extract space information of object pedestrian and disintegrate it into three local regions. In addition, employ the improved texture and colour information extract algorithm to get the joint texture and colour information from the corresponding sub-region. Finally, determine the position of object by colour-texture similarity indicator based on space division, and get the result of accurately track. In consideration of the multi thread information fusion algorithm need a larger number of particles, this factor could reduce the computational efficiency. Therefore, a wave integral histogram algorithm is proposed for improving arithmetic speed. The experiment carried out on videos, result indicates the effectiveness and efficiency of the proposed method, which can achieve higher accuracy than other tow state of the art algorithms in the actual traffic scene, and the real-time performance also has been improved considerably.

Pedestrian tracking in outdoor spaces of a suburban university campus for the investigation of occupancy patterns

The design of a livable and comfortable environment has been one of the main aims of sustainable university campus design. The creation of outdoor spaces for accommodating amenities has a positive effect on users with regard to various physiological and psychological aspects. Knowing how daily activity patterns and pedestrian movements are distributed across space is important for assessing whether or not human use and design plans are in fact successful. The aim of this study is to determine occupancy patterns and pedestrian routes in outdoor spaces during different seasons at a sustainable university campus by using spatial statistical analyses that involve ANN, MC and SDE. To perform these analyses, the researchers attempted to use a pedestrian tracking method from camera surveillance to aggregate the required data by conducting a longitudinal study. The data that were aggregated by pedestrian tracking was visualized with the use of a spatio-temporal mapping method in GIS. Logistic GWR was performed to seek the relationship between occupancy pattern (clustered distribution) and design layout of open spaces, comprising the variables of proximity to the attraction centers/entrances, and visual integration. The results confirmed that occupants prefer to use the areas that have high visual integration value and are close to attraction centers.

Design and Implementation of the Pedestrian Information Analysis System

In this paper, we proposed a pedestrian information analysis system. It is consisted of the pedestrian detection module and the pedestrian tracking module. Compared with various pedestrian detection methods, the Deformable Part Model (DPM) algorithm is used to detect the pedestrians in the picture. Meanwhile, this paper proposes a pedestrian tracking method. This method uses the pedestrian detection result to calculate the pedestrian’s centroid and uses the video time domain information to track the centroid. It can help us to obtain the pedestrian information that includes the pedestrian moving distance and direction. We set the count line to count the pedestrian’s number and direction in this system. The experiment results show that the system we proposed can analyse pedestrians more accurately.

Real-time accurate pedestrian tracking using extended finite impulse response filter bank for tightly coupling recent inertial navigation system and ultra-wideband measurements

To satisfy the increasing demands of the accuracy for the human localization, in this work, we propose a pedestrian tracking method by tightly coupling recent inertial navigation system–based and ultra-wideband–based measurements. In this mode, the difference between the distances derived from the inertial navigation system–based and ultra-wideband–based system is used as the observation of the data fusion filter. Moreover, in order to improve the performance of the extended finite impulse response filter, which depends on the averaging horizon ([Formula: see text]) when the error state vector ([Formula: see text]) is determined due to the model, the extended finite impulse response filter bank is employed to be the fusion center for pedestrian tracking, which used the Mahalanobis distance to find the optimal [Formula: see text] at each time index [Formula: see text]. Test experiments illustrate that the extended finite impulse response filter bank–based tightly coupled inertial navigation system/ultra-wideband–integrated method is able to achieve real-time estimation, and its accuracy is similar to the extended finite impulse response with the ideal [Formula: see text] which is calculated off-line.

Multiple Pedestrian Tracking From Monocular Videos in an Interacting Multiple Model Framework.

We present a multiple pedestrian tracking method for monocular videos captured by a fixed camera in an interacting multiple model (IMM) framework. Our tracking method involves multiple IMM trackers running in parallel, which are tied together by a robust data association component. We investigate two data association strategies which take into account both the target appearance and motion errors. We use a 4D color histogram as the appearance model for each pedestrian returned by a people detector that is based on the histogram of oriented gradients features. Short-term occlusion problems and false negative errors from the detector are dealt with using a sliding window of video frames, where tracking persists in the absence of observations. Our method has been evaluated, and compared both qualitatively and quantitatively with four state-of-the-art visual tracking methods using benchmark video databases. The experiments demonstrate that, on average, our tracking method outperforms these four methods.

Fast pedestrian detection and dynamic tracking for intelligent vehicles within V2V cooperative environment

Pedestrian detection has become one of the hottest topics in intelligent traffic system because of its potential applications in driver assistance and automatic driving. In this study, a fast pedestrian detection and dynamic tracking method within vehicle-to-vehicle (V2V) cooperative environment is proposed. A dynamic tracking-by-detection framework for real-time pedestrian detection is developed. First, a cascade classifiers, based on selected Haar-like features, is trained to detect pedestrian. Then, CamShift algorithm combined with extended Kalman filtering is used to pedestrian dynamic tracking. Finally, with the crowdsourcing detected information, a smartphone-based V2V cooperative warning system is developed to share useful detection results within blind spots. The experiment results show that the proposed method has a real-time and accurate performance, which can provide a reference for road traffic safety monitoring technology.