Video Monitoring Research Articles

Measuring Changes in Upper Body Movement Due to Fasting Using a Camera

Understanding activity levels during fasting is important for promoting healthy fasting practices. While most existing studies focus on step counts to objectively assess the impact of fasting on activity levels and behavioral changes, the results have been mixed. Despite evidence showing that individuals spend a significant amount of time sitting while fasting, there has been no objective measurement of body movement or activity levels during sitting and fasting. This research employs a video-based, unobtrusive human body movement measurement system to monitor upper body movements during fasting and non-fasting periods over several days. Key movement features, such as inactivity, movement speed, and movement scale, were automatically extracted from the video monitoring data using a computer vision pipeline. These features were then statistically compared using t tests between fasting and non-fasting periods, analyzed by hour of the day and across different days. The results of the monitoring of five participants during typical daily sitting office work and fasting for 3–5 days indicate no consistent pattern of upper body movement changes due to fasting among the participants.

Heuristic Optimal Scheduling for Road Traffic Incident Detection Under Computational Constraints

The intelligent monitoring of road surveillance videos is a crucial tool for detecting and predicting traffic anomalies, swiftly identifying road safety risks, rapidly addressing potential hazards, and preventing accidents or secondary incidents. With the vast number of surveillance cameras in operation, conducting traditional real-time video analysis across all cameras at once requires substantial computational resources. Alternatively, methods that employ periodic camera patrol analysis frequently overlook a significant number of anomalous traffic events, thereby hindering the effectiveness of traffic event detection. To overcome these challenges, this paper introduces a heuristic optimal scheduling approach designed to enhance traffic event detection efficiency while operating within limited computational resources. This method leverages historical data and prior knowledge to compute a weighted event feature value for each camera, providing a quantitative measure of its detection efficiency. To optimize resource allocation, a cyclic elimination mechanism is implemented to exclude low-performing cameras, enabling the dynamic reallocation of resources to higher-performing cameras, thereby enhancing overall detection performance. Finally, the effectiveness of the proposed method is validated through a case study conducted in a representative region of a major metropolitan city in China. The results revealed a substantial improvement in traffic event detection efficiency, with increases of 40%, 28%, 17%, and 28% across different time periods when compared to the pre-optimized state. Furthermore, the proposed method outperformed existing resource scheduling algorithms in terms of average load degree, load balance degree, and higher computational resource utilization. By avoiding the common issues of resource wastage and insufficiency often found in static allocation models, this approach offers greater flexibility and adaptability in computational resource scheduling, thereby effectively addressing the practical demands of traffic anomaly detection and early warning systems.

Development of a Key Method for the Optimization of Port Vessel Detection Based on an Improved Multi-Structural Morphology Approach

All over the world, many ports have implemented surveillance camera systems to monitor the vessels and activities around them. These types of systems are not very effective in accurately detecting activities around the port due to background noise and congestion interference at the sea surface. This is why it is difficult to accurately detect vessels, especially smaller vessels, when it turns dark. It is known that some vessels do not comply with maritime rules, particularly in port and safety zones; these must be detected to avoid incidents. For these reasons, in this study, we propose and develop an improved multi-structural morphology (IMSM) approach to eliminate all of this noise and interference so that vessels can be accurately detected in real time. With this new approach, the target vessel is separated from the sea surface background through the weighted morphological filtering of several datasets of structural components. Then, neighborhood-based adaptive fast median filtering is used to filter out impulse noise. Finally, a characteristic morphological model of the target vessel is established using the connected domain; this allows the sea surface congestion to be eliminated and the movement of vessels to be detected in real time. Multiple tests are carried out on a small and discrete area of moving vessels. The results from several collected datasets show that the proposed approach can effectively eliminate background noise and congestion interference in video monitoring. The detection accuracy rate and the processing time are improved by approximately 3.91% and 1.14 s, respectively.

Beach Area Changes and Resilience of the Eastern Coasts Before and After Typhoon Goni

<i>Due to climate change, waves have become increasingly stronger, making the analysis of beach changes before and after typhoons crucial for addressing beach erosion. This study utilized low-cost, high-efficiency video monitoring to analyze beach changes at 14 locations along Korea's east coast before and after typhoon impacts. Shorelines were extracted from 180 s average orthoimages using the Pixel Intensity Moving Average Extraction technique, and beach areas were calculated. The study focused on the recovery period following typhoon-induced erosion. During Typhoon Goni (2015), erosion reached up to 38% at Bongpo Beach, with a maximum affected area of 7,741 m<sup>2</sup> at Goraebul Beach. Post-typhoon recovery exceeded 89%, with most beaches returning to pre-typhoon conditions. The erosion period averaged 7 d, while recovery took approximately 27 d. Erosion was significantly influenced by natural forces such as waves, tides, and wind. The erosion period showed minimal correlation with wave energy, whereas the recovery period exhibited some correlation. Further long-term analysis, incorporating additional wave data and typhoon impact periods, is needed. Future research will aim to collect extensive typhoon data to systematically analyze erosion and recovery cycles in relation to external forces.</i>

A Review of Intelligent Depth Distance Perception Research for Power Transmission Line Corridor Scenarios

Transmission lines are essential carriers for the transmission of electrical energy, and their safe operation is fundamental to ensuring reliable power supply. However, the environment of transmission line corridors is complex and variable, posing numerous risks of external damage. With the development of smart power systems, information technologies such as video monitoring provide effective means for monitoring and managing external damage to transmission lines. Nonetheless, the current technology for identifying external damage and safe distances for transmission lines is weak, leading to frequent false alarms and low efficiency in practical applications. To address this issue, this paper systematically reviews and summarizes the progress of distance recognition technology in power systems. First, it outlines the spatial distance perception performance requirements for models in transmission line corridor scenarios and summarizes the spatial distance data characteristics of these corridors. Second, the paper categorizes existing common safety distance recognition methods from the perspectives of active and passive ranging, analyzing their advantages and disadvantages in the context of transmission line corridors. Finally, this paper summarizes the types and performance characteristics of current deep learning-based distance recognition methods and proposes a potential application framework for these methods in transmission line corridor scenarios. It also discusses the future application prospects and challenges faced by this framework.

Riluzole attenuates acute neural injury and reactive gliosis, hippocampal-dependent cognitive impairments and spontaneous recurrent generalized seizures in a rat model of temporal lobe epilepsy.

Riluzole exhibits neuroprotective and therapeutic effects in several neurological disease models associated with excessive synaptic glutamate (Glu) release. We recently showed riluzole prevents acute excitotoxic hippocampal neural injury at 3days in the kainic acid (KA) model of temporal lobe epilepsy (TLE). Currently, it is unknown if preventing acute neural injury and the neuroinflammatory response is sufficient to suppress epileptogenesis. The KA rat model of TLE was used to determine if riluzole attenuates acute hippocampal neural injury and reactive gliosis. KA was administered to adult male Sprague-Dawley (250g) rats at 5mg/kg/hr until status epilepticus (SE) was observed, and riluzole was administered at 10mg/kg 1h and 4h after SE and once per day for the next 2days. Immunostaining was used to assess neural injury (FJC and NeuN), microglial activation (Iba1 and ED-1/CD68) and astrogliosis (GFAP and vimentin) at day 7 and day 14 after KA-induced SE. Learning and memory tests (Y-maze, Novel object recognition test, Barnes maze), behavioral hyperexcitability tests, and spontaneous generalized recurrent seizure (SRS) activity (24-hour video monitoring) were assessed at 11-15weeks. Here we show that KA-induced hippocampal neural injury precedes the neuroimmune response and that riluzole attenuates acute neural injury, microglial activation, and astrogliosis at 7 and 14days. We find that reducing acute hippocampal injury and the associated neuroimmune response following KA-induced SE by riluzole attenuates hippocampal-dependent cognitive impairment, behavioral hyperexcitability, and tonic/clonic generalized SRS activity after 3months. We also show that riluzole attenuates SE-associated body weight loss during the first week after KA-induced SE. Riluzole acts on multiple targets that are involved to prevent excessive synaptic Glu transmission and excitotoxic neuronal injury. Attenuating KA-induced neural injury and subsequent microglia/astrocyte activation in the hippocampus and extralimbic regions with riluzole reduces TLE-associated cognitive deficits and generalized SRS and suggests that riluzole could be a potential antiepileptogenic drug.

Agent-based modeling system for real-time characterization of film thickness in digital twin coating

In the automated spraying workshop of ship segments, poor visibility caused by dust and fog hampers the effectiveness of the video monitoring system. The traditional method used during the automated spraying process fails to provide real-time measurement of film thickness and prediction of spraying quality, resulting in uneven film thickness and high rework rates. Robotic spraying technology also faces challenges, such as the time-consuming and labor-intensive process of building and computing a highly reliable Computational Fluid Dynamics (CFD) based spraying film-forming simulation model, which cannot be reflected in real-time during the spraying process. The digital twin characterization method, based on the agent model, offers a solution to these limitations and challenges, providing new ideas and approaches for improving and optimizing the spray film formation model. This paper presents the development of a real-time characterization system for sprayed film thickness based on digital twin technology. The spraying film thickness under different working conditions is obtained using Ansys-Fluent simulation software by varying the gun height and gun speed. The predictive model for spraying film thickness is then established using the obtained simulation data and the corresponding gun height and gun speed, employing the surrogate modeling method (BP neural network). The real-time characterization system for spraying film thickness is developed by combining C# and Unity3D. Finally, in order to ensure the accuracy of the predictive model, a spraying experimental platform is built to verify the accuracy of the predictive model.

Investigation of the Influence of Different Filler Contents of Wine Pomace in PBS on Fracture Mechanics Properties

Biobased polybutylene succinate (PBS) represents a promising alternative to petrochemical-based polymers. The use of this biopolymeris limited in many areas by its low resilience against environmental influences. With the help of bio-based stabilizers the thermo-oxidative degradation process can be slowed down. Suitable stabilizing additives are natural antioxidants present in plant extracts with a high flavonoid content, which can be found in grapes, wine and wine by-products. PBS was modified with two different bio-stabilizers based on wine grape pomace. The highest filler content tested was 20 wt.-%. In addition to improving stability, the additives also impact the polymer’s mechanics. The influence of these functional fillers on the fracture mechanical properties was examined in a quasi-static test. The crack growth was recorded using integrated video monitoring. Based on the results, the corresponding crack resistance curve and tearing modulus were determined depending on filler type and content. Additional optical analysis was used to correlate fracture mechanics and structure. The two bio-stabilizers based on red (RWP) and white wine pomace (WWP) differs distinctly in terms of their influence on fracture mechanical properties. The Influence of RWPon the fracture toughness is significantly higher than that of WWP. Especially at lower filler contents with RWP, there is a strong increase in the fracture mechanics parameter tearing modulus (TJ) and an increase in the slope of the R-curve. With 5 wt.% RWP DOM the TJ is 13.64 x 102, whereas with WWP Silv a value of only 6.39 x 102 can be achieved. This difference is also reflected in the increase in the R-curves. With 5 wt.% a slope of the fitted R-curve of 265.59 (RWP DOM) and 121.02 (WWP Silv) could be determined with the first derivative. In the optical analysis it was noticeable that the RWP particles were more homogeneously dispersed in the matrix while the WWP filler tended to agglomerate. The inhomogeneous distribution and strong agglomeration tendency can be attributed to a higher sugar content of WWP and a higher particle size distribution. The top cut (D97) of WWP Silv is 62.37 ± 0.05 µm and that of RWP DOM is 51.97 ± 0.09 µm.

Small Target Detection Algorithm Based on Improved YOLOv5

Small targets exist in large numbers in various fields. They are broadly used in aerospace, video monitoring, and industrial detection. However, because of its tiny dimensions and modest resolution, the precision of small-target detection is low, and the erroneous detection rate is high. Therefore, based on YOLOv5, an improved small-target detection model is proposed. First, in order to improve the number of tiny targets detected while enhancing small-target detection performance, an additional detection head is added. Second, involution is used between the backbone and neck to increase the channel information of feature mapping. Third, the model introduces the BiFormer, wherein both the global and local feature information are captured simultaneously by means of its double-layer routing attention mechanism. Finally, a context augmentation module (CAM) is inserted into the neck in order to maximize the structure of feature fusion. In addition, in order to consider among the required real frame as well as the prediction frame simultaneously, YOLOv5’s original loss function is exchanged. The experimental results using the public dataset VisDrone2019 show that the proposed model has P increased by 13.43%, R increased by 11.28%, and mAP@.5 and mAP@[.5:.95] increased by 13.88% and 9.01%, respectively.

TRANscranial direct current stimulation for FOcal Refractory epilepsy in mitochondrial disease (TRANSFORM): delayed-start, randomised, double-blinded, placebo-controlled study

BackgroundFocal epilepsy is common in children and adults with mitochondrial disease. Seizures are often refractory to pharmacological treatment and, in this patient group, frequently evolve to refractory focal status epilepticus (also known as epilepsia partialis continua). Where this occurs, the long-term prognosis is poor. Transcranial DC stimulation (tDCS) is a promising, non-invasive, adjunctive treatment alternative to common surgical procedures. Limited recruitment of study participants with this rare disease and the ethical challenges of administering a treatment to one group and not another, while maintaining strict methodological rigour can pose challenges to the design of a clinical study.MethodWe designed the first delayed start, double-blinded, sham-controlled study to evaluate the efficacy of tDCS as an adjunctive treatment for focal epilepsy. We will include participants with a genetically confirmed diagnosis of mitochondrial disease with drug-resistant focal epilepsy aged ≥ 2 years, aiming to collect 30 episodes of focal status epilepticus, each treated for a maximum period of 14 days. The early start intervention arm will receive tDCS from day 1. The delayed start intervention arm will receive sham stimulation until crossover on day 3. Our primary endpoint is a greater than 50% reduction from baseline (on day 0) in seizure frequency assessed by 3x daily reporting, accelerometery, and video monitoring. Changes in the underlying epileptogenic focus within the brain related to the tDCS intervention will be assessed by magnetic resonance imaging (MRI) and/or electroencephalography (EEG).DiscussionStudy results in favour of treatment efficacy would support development of tDCS into a mainstream treatment option for focal epileptic seizures related to mitochondrial disease.Trials registrationISRCTN: 18,241,112; registered on 16/11/2021.

Deep Learning-Based Camouflaged Object Detection and Tracking for Enhanced Video Surveillance

To improve security and tactical awareness, video surveillance systems need to be able to find and track objects that are hidden. The approach suggests a deep learning-based method for finding and following hidden objects. There are two major steps in our method: finding and following. During the detecting step, we use a R-CNN based model to find items that are hidden in each frame. A lot of labelled pictures with different kinds of camouflage patterns and objects are used to train this model. The updated Faster R-CNN has more levels and changes that make it better at finding things that are hidden. To keep track of the objects across frames, we use an LSTM-based tracker. The LSTM tracker uses the object's traits and motion information to keep track of its state and guess where it will be in the next frame. To make our method even more effective, we use pre-trained models like MobileNet and VGG-19 for feature extraction. This makes the computations simpler while keeping the accuracy of the recognition and tracking high. The proposed model tested on a number of difficult video scenes with items that were well hidden. The results show that our method works better than other methods, as it increases the accuracy of both recognition and tracking. Also, our method works well even when the lighting changes, the size of the objects changes, or the background is complicated. The suggested method based on deep learning looks like a good way to find and follow hidden objects in video monitoring scenarios. Using CNNs, LSTM networks, and pre-trained models like MobileNet and VGG-19, we show big improvements in terms to compare the various performance parameters with accuracy and stability, which helps make security and monitoring systems better.

Energetics explain predator occurrence and movement in pyrodiverse landscapes

ContextFire-adapted species have evolved to exploit resources in heterogenous landscapes that presumably maximize energy acquisition and minimize energetic expenditure. However, limited empirical work exists demonstrating the explicit energetic mechanisms that drive such adaptive responses to fire across diverse landscapes.ObjectivesThe California spotted owl (Strix occidentalis occidentalis) appears to benefit from landscape heterogeneity and preferentially uses smaller patches of severely burned forest, a behavior that has been hypothesized as adaptive. Here, we investigate empirical support for this hypothesis.MethodsWe leveraged high-resolution GPS tracking and nest video monitoring to examine the hunting success, movement, and nest provisioning of 34 spotted owls in the Sierra Nevada and San Bernardino Mountains, California across burned and unburned landscapes.ResultsRegardless of time since fire, individuals avoided foraging directly within moderately or severely burned patches. 1 to 2 years post-fire, individuals had more success capturing prey in unburned forest, and the energy individuals spent moving increased with the proportion of high-severity fire and decreased with the proportion unburned forest. Multiple years after a fire, individuals had more success capturing prey, spent less energy moving, and provisioned more energy to nests in landscapes with more low-severity fire.ConclusionsThese results support the hypothesis that spotted owls are adapted to fire-prone landscapes and that disturbance events within this region’s natural range of variation can ultimately promote hunting and provisioning. As fires deviate from regional norms across the globe, the negative impacts of fire may become more extreme and long-term benefits of fire may degrade for animals in fire-prone landscapes. Examining the mechanistic impacts of disturbance can allow us to better understand animal responses to rapidly changing landscapes.

Nest Box Cameras Provide Insight into Causes of Nest Failure for American Kestrels

ABSTRACT Although nest failure is a common occurrence in birds, oftentimes the causes, or details, of the failure are unknown because nests cannot be monitored closely or continuously. This inability to monitor nests in ways that allow for a detailed understanding of nest failure can hamper our ability to conserve declining species, such as the American Kestrel (Falco sparverius). Here we describe previously unreported observations from continuous video monitoring in kestrel nest boxes and biweekly nest monitoring via an extendable fiber optic endoscopic camera. From continuous video monitoring we observed adult kestrels consume a kestrel egg with little to no development and a European Starling (Sturnus vulgaris) pierce and remove an abandoned kestrel egg from a nest box. From biweekly monitoring with a fiber optic camera, we inferred that nest abandonment by kestrels was associated with eggs not developing either from infertility or early-stage embryo death. Although it is unclear how common such occurrences may be across the broader range of kestrels, these observations may provide impetus to explore these causes of nest failure more closely.

Towards automatic farrowing monitoring-A Noisy Student approach for improving detection performance of newborn piglets.

Nowadays, video monitoring of farrowing and automatic video evaluation using Deep Learning have become increasingly important in farm animal science research and open up new possibilities for addressing specific research questions like the determination of husbandry relevant indicators. A robust detection performance of newborn piglets is essential for reliably monitoring the farrowing process and to access important information about the welfare status of the sow and piglets. Although object detection algorithms are increasingly being used in various scenarios in the field of livestock farming, their usability for detecting newborn piglets has so far been limited. Challenges such as frequent animal occlusions, high overlapping rates or strong heterogeneous animal postures increase the complexity and place new demands on the detection model. Typically, new data is manually annotated to improve model performance, but the annotation effort is expensive and time-consuming. To address this problem, we propose a Noisy Student approach to automatically generate annotation information and train an improved piglet detection model. By using a teacher-student model relationship we transform the image structure and generate pseudo-labels for the object classes piglet and tail. As a result, we improve the initial detection performance of the teacher model from 0.561, 0.838, 0.672 to 0.901, 0.944, 0.922 for the performance metrics Recall, Precision and F1-score, respectively. The results of this study can be used in two ways. Firstly, the results contribute directly to the improvement of piglet detection in the context of birth monitoring systems and the evaluation of the farrowing progress. Secondly, the approach presented can be transferred to other research questions and species, thereby reducing the problem of cost-intensive annotation processes and increase training efficiency. In addition, we provide a unique dataset for the detection and evaluation of newborn piglets and sow body parts to support researchers in the task of monitoring the farrowing process.

VIOLENCE PREDICTION IN SURVEILLANCE VIDEOS

Forecasting violence has become a critical obstacle in the field of video monitoring to guarantee public safety. Lately, YOLO (You Only Look Once) has become a popular and effective method for detecting weapons. However, identifying and forecasting violence remains a challenging endeavor. Additionally, the classification results had to be enhanced with semantic information. This study suggests a method for forecasting violent incidents by utilizing Yolov9 and ontology. The authors employed Yolov9 to identify and categorize weapons and individuals carrying them. Ontology is utilized for semantic prediction to assist in predicting violence. Semantic prediction happens through the application of a SPARQL query to the identified frame label. The authors developed a Threat Events Ontology (TEO) to gain semantic significance. The system was tested with a fresh dataset obtained from a variety of security cameras and websites. The VP Dataset comprises 8739 images categorized into 9 classes. The authors examined the outcomes of using Yolov9 in conjunction with ontology in comparison to using Yolov9 alone. The findings show that by combining Yolov9 with ontology, the violence prediction system's semantics and dependability are enhanced. The suggested system achieved a mean Average Precision (mAP) of 83.7 %, 88% for precision, and 76.4% for recall. However, the mAP of Yolov9 without TEO ontology achieved a score of 80.4%. It suggests that this method has a lot of potential for enhancing public safety. The authors finished all training and testing processes on Google Colab's GPU. That reduced the average duration by approximately 90.9%. The result of this work is a next level of object detectors that utilize ontology to improve the semantic significance for real-time end-to-end object detection.

Chaotic Encryption-Based Network Robot for Indoor Security and Remote Video Monitoring

Chaotic Encryption-Based Network Robot for Indoor Security and Remote Video Monitoring

Visible and near‐infrared image fusion based on information complementarity

AbstractImages with complementary spectral information can be recorded using image sensors that can identify visible and near‐infrared spectrum. The fusion of visible and near‐infrared (NIR) aims to enhance the quality of images acquired by video monitoring systems for the ease of user observation and data processing. Unfortunately, current fusion algorithms produce artefacts and colour distortion since they cannot make use of spectrum properties and are lacking in information complementarity. Therefore, an information complementarity fusion (ICF) model is designed based on physical signals. In order to separate high‐frequency noise from important information in distinct frequency layers, the authors first extracted texture‐scale and edge‐scale layers using a two‐scale filter. Second, the difference map between visible and near‐infrared was filtered using the extended‐DoG filter to produce the initial visible‐NIR complementary weight map. Then, to generate a guide map, the near‐infrared image with night adjustment was processed as well. The final complementarity weight map was subsequently derived via an arctanI function mapping using the guide map and the initial weight maps. Finally, fusion images were generated with the complementarity weight maps. The experimental results demonstrate that the proposed approach outperforms the state‐of‐the‐art in both avoiding artificial colours as well as effectively utilising information complementarity.

Continuous Video Monitoring of Zoo Cheetahs (Acinonyx jubatus jubatus) Reveals Differential Engagement Patterns for Environmental Enrichment Items Based on Sensory Category

Strategically enriching the environment of zoo felids to encourage innate behaviors is essential to good welfare. To investigate how engagement differs among sensory-based enrichment, six items representing tactile (firehose log, Jolly Eggs), visual (mirror, movie), and olfactory (cinnamon, cologne) sensory categories were offered to three adult cheetah siblings. Each item was offered four times: twice during daytime hours and twice overnight (≥5 h/occasion). Static video monitoring was used to investigate engagement frequency and duration for each item and to observe grooming behaviors. Cheetahs engaged with visual enrichment more frequently (p < 0.05) and for greater (p < 0.05) periods than other items. Allogrooming occurred most frequently (p < 0.05) when the movie was provisioned at night. Tactile enrichment was only modestly engaged, with fewer but longer engagements (p < 0.05) at nighttime than at daytime. Autogrooming frequency did not vary among enrichment items but was greater (p < 0.05) at night than day. These findings showed that zoo cheetah responses to sensory enrichment items differed based on type and time of day. Visual stimuli were favored, whereas olfactory stimuli were generally ignored. This illustrates the benefit of diverse sensory-specific enrichment strategies. Such dynamic strategies can help overcome the challenge of individual preferences to encourage engagement reflective of the animal’s natural behaviors.

GCP Placement Methods for Improving the Accuracy of Shoreline Extraction in Coastal Video Monitoring

In coastal video monitoring, the direct linear transform (DLT) method with ground control points (GCPs) is commonly used for geo-rectification. However, current practices often overlook the impact of GCP quantity, arrangement, and the geographical characteristics of beaches. To address this, we designed scenarios at Chuam Beach to evaluate how factors such as the distance from the camera to GCPs, the number of GCPs, and the height of each point affect the DLT method. Accuracy was assessed by calculating the root mean square error of the distance errors between the actual GCP coordinates and the image coordinates for each setting. This analysis aims to propose an optimal GCP placement method. Our results show that placing GCPs within 200 m of the camera ensures high accuracy with few points, whereas positioning them at strategic heights enhances shoreline extraction. However, since only fixed cameras were used in this study, factors like varying heights, orientations, and resolutions could not be considered. Based on data from a single location, we propose an optimal method for GCP placement that takes into account distance, number, and height using the DLT method.

Optimized Deep LSTM-Based Multi-Object Tracking with Occlusion Handling Mechanism

The multi-object tracking is a basic computer vision process having a huge class of real-life tools that range from monitoring of medical video to surveillance. The goal of tracking numerous items is to place numerous objects in a scene, handle their identities throughout time, and construct trajectories for analysis. However, this is a complex task, because of certain issues like occlusions, complicated object dynamics, and variations in the appearance of objects. In this research, a new technique named TPRO-based Deep LSTM is developed for tracking multi-object with occlusion handling. Here, the videos are considered as input wherein the extraction of frames is done from each video. Each frame undergoes pre-processing with filtering to eliminate noise from frames. By using a sparse Fuzzy c-Means (FCM) and Local Optimal-Oriented Pattern (LOOP) features, the localization of objects is done. Moreover, the visual and spatial trackings are considered for hybrid tracking. The second derivative model and neighborhood search model are used to perform visual tracking. Then the occlusion handling is performed. Concurrently, with the use of Deep Long Short-Term Memory (Deep LSTM) the spatial tracking is performed and the Taylor Poor Rich Optimization (TPRO) algorithm assigns the weight and bias of the Deep LSTM. The TPRO is obtained by the unification of the Taylor series along with the Poor and Rich Optimization algorithm. By combining visual and spatial tracking, the final tracked output is generated. The devised method achieves a performance with the highest value of 88.9% for Multiple Object Tracking Precision (MOTP), smallest tracking distance (TD) of 4.185, average MOTP of 0.889, average TD of 4.201, and highest tracking number (TN) of 14.