Real-time Motion Detection Research Articles

High-Performance Stretchable Strain Sensors Based on Auxetic Fabrics for Human Motion Detection.

Wearable strain sensors play a pivotal role in real-time human motion detection and health monitoring. Traditional fabric-based strain sensors, typically with a positive Poisson's ratio, face challenges in maintaining sensitivity and comfort during human motion due to conflicting resistance changes in different strain directions. In this work, high-performance stretchable strain sensors are developed based on graphene-modified auxetic fabrics (GMAF) for human motion detection in smart wearable devices. The proposed GMAF sensors, with a negative Poisson's ratio achieved through commercially available warp-knitting technology, exhibit an 8-fold improvement in sensitivity compared to conventional plain fabric sensors. The unique auxetic fabric structure enhances sensitivity by synchronizing resistance changes in both wale and course directions. The GMAF sensors demonstrate excellent washability, showing only slight degradation in auxeticity and an acceptable increase in resistance after 10 standard wash cycles. The GMAF sensors maintain stability under different strain levels and various motion frequencies, emphasizing their dynamic performance. The sensors exhibit superior conformability to joint movements, which effectively monitor a full range of motions, including joint bending, sports activities, and subtle actions like coughing and swallowing. The research underscores a promising approach to achieve industrial-scale production of wearable sensors with improved performance and comfort through fabric structure design.

Enhanced multifunctional sensing in human motion with speed-controlled coaxial wet-spun hollow MWCNT-TPU/TPU smart fibers

In the field of personal health management and athletic performance optimization, the demand for multi-parameter human signal monitoring devices is rapidly increasing. Currently, flexible sensors produced through wet spinning techniques face challenges of simplistic structure and functionality, as well as difficulty in balancing strength and sensitivity. In-depth research is needed to develop high-performance wet spinning techniques, which will lay the foundation for commercial smart garments capable of unobtrusively monitoring human motion in the future. This study innovatively employs specialized slurry formulations and spinning speed controls to utilize the timing differences in fiber precipitation and the affinity among similar materials. Through the coaxial wet spinning process, it enables the continuous, large-scale manufacturing of hollow core–shell fibers, MT/T-S5, which feature a dense inner layer and a porous outer conductive layer. This special structure endows the fibers with high strength, high signal stability, and capabilities for both active and passive heating. These fibers achieve a maximum gauge factor (GF) 65.2 in stretch sensing applications and can detect pressures as low as 0.1 N. The MT/T-S5 smart fibers can sense human joint movements, and through connection with an Arduino microcontroller, they can control a robotic hand and perform independent and real-time motion detection of five fingers to distinguish gestures. This research not only provides a new type of fiber material for the development of future smart textiles but also reveals a formation mechanism for hollow core–shell fibers in the field of wet spinning. This discovery can offer valuable inspiration for fiber structural design in future research.

Optimizing motion detection performance: Harnessing the power of squeeze and excitation modules.

This paper introduces an innovative segmentation model that extends the U-Net architecture with a Squeeze and Excitation (SE) mechanism, designed to enhance the detection of moving objects in video streams. By integrating this model into the ViBe motion detection algorithm, we have significantly improved detection accuracy and reduced false positive rates. Our approach leverages adaptive techniques to increase the robustness of the segmentation model in complex scenarios, without requiring extensive manual parameter tuning. Despite the notable improvements, we recognize that further training is necessary to optimize the model for specific applications. The results indicate that our method provides a promising direction for real-time motion detection systems that require high precision and adaptability to varying conditions.

Graphene-Infused Sustainable Rubber-Based Triboelectric Nanogenerator For Real-Time Human Motion Monitoring.

Triboelectric nanogenerators (TENG) are promising alternatives for clean energy harvesting. However, the material utilization in the development of TENG relies majorly on polymers derived from non-renewable resources. Therefore, minimizing the carbon footprint associated with such TENG development demands a shift toward usage of sustainable materials. This study pioneers using natural rubber (NR) as a sustainable alternative in TENG development. Infusing graphene in NR, its dielectric constant and tribonegativity are optimized, yielding a remarkable enhancement. The optimized sample exhibits a dielectric constant of 411 (at 103Hz) and a contact potential difference (CPD) value of 1.85V. In contrast, the pristine NR sample showed values of 6 and 3.06V for the dielectric constant and CPD. Simulation and experimental studies fine-tune the TENG's performance, demonstrating excellent agreement between theoretical predictions and practical studies. Sensors developed via stencil printing technique possess a remarkably low layer thickness of 270µm, and boast a power density of 420mWm-2, a staggering 250% increase over conventional NR. Moreover, the material is pressure sensitive, enabling precise real-time human motion detection, including finger contact, finger bending, neck bending, and arm bending. This versatile sensor offers wireless monitoring, empowering healthcare monitoring based on the Internet of Things.

Deep Learning-Based Intelligent Video Surveillance System for Real-Time Motion Detection

The proliferation of surveillance systems demands advanced solutions to effectively monitor and analyze video feeds for security and safety purposes. In this paper, we propose a Deep Learning-Based Intelligent Video Surveillance System (DIVSS) designed to enhance traditional Closed-Circuit Television (CCTV) setups. DIVSS integrates state-of-the-art deep learning techniques for real-time motion detection and object recognition, enabling proactive threat detection and automated response mechanisms. The system utilizes convolutional neural networks (CNNs) for robust feature extraction and classification, enabling accurate identification of objects of interest amidst complex backgrounds and varying[1] lighting conditions. Furthermore, DIVSS incorporates region of interest (ROI) monitoring to focus attention on specific areas within the surveillance footage, optimizing computational resources and improving response times. We evaluate the performance of DIVSS through comprehensive experiments conducted on diverse surveillance scenarios, demonstrating its effectiveness in enhancing security measures and providing actionable[3] insights for surveillance operators. The proposed system represents a significant advancement in video surveillance technology, offering unparalleled capabilities for proactive threat detection and real-time response in dynamic environments. Keywords— Deep learning has transformed video surveillance, enabling real-time motion detection and object recognition using Convolutional Neural Networks (CNNs). This technology provides proactive threat detection, intelligent systems for ROI monitoring, and enhances overall security measures.

Ultra-stretchable and highly tough ionogels with underwater repeatable adhesion and anti-swelling capacity for real-time motion detection, signal transmission and electrochemical monitoring platforms

Hydrophobic ionogels have received growing interest as a flexible underwater sensing material. However, it remains a significant challenge to improve the tensile properties, prolonged underwater repeatable adhesion, and multifunctionality of the hydrophobic ionogel due to the restricted selection of monomers and curing strategies. Herein, a hydrophobic multifunctional fluorine-rich ionogel with ultra-stretchability and superior long-term underwater repeatable adhesion is designed by virtue of the introduction of a rigid and flexible macromolecular cross-linker and a structure of rigid cationic imidazole-benzene rings in a hydrophobic ionic liquid monomer. The macromolecular cross-linker significantly improves the mechanical properties of the ionogel because of the reduction in stress concentration. And the structure of short imidazole-benzene rings with high rigidity exposes a larger amount of adhesion groups on the surface of the ionogels compared to the flexible groups, leading to enhanced long-term underwater repeatable adhesion performance of the ionogel. The ionogels are applied to real-time monitoring of exposure to water, underwater swimming motion monitoring, underwater Morse code transmission and electrochemical monitoring platforms. And this work is expected to provide ideas for the multifunctionalization of underwater sensing technology and the integration of functional units in underwater flexible electronic skin.

IOT Pada Purwarupa Sistem Keamanan Pintu Kantor Dengan Sensor RFID dan PIR Berbasis Telegram

The proposed office door security system combines RFID (Radio-Frequency Identification) Sensor and PIR (Passive Infrared) Sensor technology with Telegram-based communication. The design of this system requires RFID and PIR sensors to be formed in order to produce a system design that is made to meet the needs of system users. The aim of this system is to increase the security level of access to office space by combining identification of access owners via RFID cards and motion detection using PIR sensors. Communication through the Telegram platform is used to provide real-time notifications to access owners when there is activity at the office door. The control system for this device is controlled by the Esp32 Microcontroller, using 4 inputs, namely Rfid, PIR, Keypad and telegram sensors, as well as 5 outputs, namely Selenid Doorlock, Buzzer, LCD, Relay and telegram. By using the esp32 microcontroller to process data and the telegram application for IoT as a link between devices and smartphones. With 2 sensors as logic inputs for the esp32 microcontroller, the number of outputs that occur is 5, namely in the form of a sound from a buzzer as a warning, and a PIR as a sensor to open the door from the inside. When opening the RFID with a card tag, then the selenoid doorlock will open. Overall, the design of this office door security system has the potential to improve security and monitoring in the office space. By combining the technology of RFID sensors, PIR sensors and Telegram-based communication, this system enables accurate identification, real-time motion detection and fast interaction between the security system and the access owner. So that Telegram is successful in sending notifications if someone enters, that is, they will appear. "User Name Open Door: according to the registered UID", but if it fails "Unregistered User Failed Login Attempt" The LCD will also issue an output if someone has registered their RFID tag or not

Ultrathin CNTs Film Based on Marangoni Effect for Strain Sensing Application

The Marangoni effect has been applied in the preparation of large-area ultrathin films. However, defects occur frequently during the transfer progress of ultrathin films to substrates, which limits its application in scalable and massive fabrication. Carbon nanotubes (CNTs), as typical one-dimensional carbon materials, are widely used in wearable and flexible sensors due to their outstanding electrical and mechanical properties. In this paper, Marangoni-driven self-assembled CNTs film was obtained by injecting 0.5 mL 1 mg·mL−1 CNTs/ethanol dispersion on 100 cm2 water dropwise; the thickness, sheet resistance, and optical transmittance (at 550 nm) of the as-prepared ultrathin film were 38 nm, 7.3 kΩ/□, and 66.9%, respectively. The CNTs film was transferred onto polydimethylsiloxane (PDMS) to prepare a conductive composite of CNTs/PDMS film and the sheet resistance of the composite film reached 21.0 kΩ/□. Furthermore, the packaged PDMS/CNTs/PDMS (PCP) strain sensors with a sandwich-like structure exhibited satisfactory sensitivity with a gauge factor of 3.4 at 50% strain, a large working range (89%), and excellent stability (>8000 cycles). The easy-making and low-cost sensors show great potential in wearable electronics, real-time motion detection, and electronic skin.

Optimal design and fabrication of stable ordered porous conductive structure for flexible strain sensors with high sensitivity and linearity

The increasing utilization of wearable electronics in human-computer interaction and medical health urges the rapid development of flexible strain sensors. However, it is still a challenge to fabricate flexible strain sensors with high sensitivity, linearity, and stability. Herein, we presented a freezing/magnetic orientation approach to construct dual-ordered porous conductive networks based on the reduced graphene oxide (rGO)/Fe nanowire (NW)/carboxymethyl cellulose (CMC) to optimize the sensing performance of the flexible strain sensors. Owing to the stable and ordered porous conductive network constructed by ice template-assisted rGO and magnetic field-induced Fe NW, the sensing performances of rGO/Fe NW/CMC ordered network composite were significantly improved. The prepared rGO/Fe NW/CMC strain sensor demonstrated a high gauge factor of 112.44, which was 426.90 % and 108.06 % higher than the samples with only ordered Fe NW network and only ordered rGO network, respectively. Meanwhile, the rGO/Fe NW/CMC strain sensor presented a linearity of 0.99 and a stability over 3000 dynamic stretching cycles, which was better than the sample without Fe NW and ordered rGO network. Owing to the excellent sensing performance, the rGO/Fe NW/CMC strain sensors were successfully used to monitor the human gestures, indicating the potential as practical wearable devices for real-time motion detection in human-computer interaction and medical health.

Shoe configuration effects on third phalanx and capsule motion of unaffected and laminitic equine hooves in-situ.

Equine shoes provide hoof protection and support weakened or damaged hoof tissues. Two hypotheses were tested in this study: 1) motion of the third phalanx (P3) and hoof wall deformation are greater in laminitic versus unaffected hooves regardless of shoe type; 2) P3 displacement and hoof wall deformation are greatest while unshod (US), less with open-heel (OH), then egg-bar (EB) shoes, and least with heart-bar (HB) shoes for both hoof conditions. Distal forelimbs (8/condition) were subjected to compressive forces (1.0x102-5.5x103 N) while a real-time motion detection system recorded markers on P3 and the hoof wall coronary band, vertical midpoint, and solar margin. Magnitude and direction of P3 displacement and changes in proximal and distal hemi-circumference, quarter and heel height and proximal and distal heel width were quantified. Hoof condition and shoe effects were assessed with 2-way ANOVA (p<0.05). P3 displacement was greater in laminitic hooves when US or with OH, and EB and HB reduced P3 displacement in laminitic hooves. P3 displacement was similar among shoes in unaffected hooves and greatest in laminitic hooves with OH, then US, EB and HB. EB and HB increased P3 displacement from the dorsal wall in unaffected hooves and decreased it in laminitic hooves. OH and EB increased P3 motion from the coronary band in laminitic hooves, and HB decreased P3 motion toward the solar margin in unaffected and laminitic hooves. In laminitic hooves, HB reduced distal hemi-circumference and quarter deformation and increased heel deformation and expansion. Proximal hemi-circumference constriction was inversely related to proximal heel expansion with and without shoes. Overall, shoe configuration alters hoof deformation distinctly between unaffected and laminitic hooves, and HB provided the greatest P3 stability in laminitic hooves. These unique results about P3 motion and hoof deformation in laminitic and unaffected hooves inform shoe selection and design.

In Situ Polymerized MXene/Polypyrrole/Hydroxyethyl Cellulose-Based Flexible Strain Sensor Enabled by Machine Learning for Handwriting Recognition.

Flexible strain sensors have significant progress in the fields of human-computer interaction, medical monitoring, and handwriting recognition, but they also face many challenges such as the capture of weak signals, comprehensive acquisition of the information, and accurate recognition. Flexible strain sensors can sense externally applied deformations, accurately measure human motion and physiological signals, and record signal characteristics of handwritten text. Herein, we prepare a sandwich-structured flexible strain sensor based on an MXene/polypyrrole/hydroxyethyl cellulose (MXene/PPy/HEC) conductive material and a PDMS flexible substrate. The sensor features a wide linear strain detection range (0-94%), high sensitivity (gauge factor 357.5), reliable repeatability (>1300 cycles), ultrafast response-recovery time (300 ms), and other excellent sensing properties. The MXene/PPy/HEC sensor can detect human physiological activities, exhibiting excellent performance in measuring external strain changes and real-time motion detection. In addition, the signals of English words, Arabic numerals, and Chinese characters handwritten by volunteers measured by the MXene/PPy/HEC sensor have unique characteristics. Through machine learning technology, different handwritten characters are successfully identified, and the recognition accuracy is higher than 96%. The results show that the MXene/PPy/HEC sensor has a significant impact in the fields of human motion detection, medical and health monitoring, and handwriting recognition.

Health Detection System for Sports Dancers during Training Based on an Image Processing Technology.

Dance sport is a competition of athletes for qualities such as speed, strength, endurance, flexibility, and coordination, requiring a high level of overall physical fitness. As China's sports fever continues to heat up, especially among students, the active nature of young people can lead to overenthusiasm for sports, dance, and other sports, which can lead to various physical discomforts during sports. Especially in the current sports habits of students, there is a great hidden danger of sports injuries. It is mainly due to excessive exercise, irregular exercise methods, and incomplete sports protective equipment. On this basis, this study proposes a model to further assess the health status of individuals and groups from the rate of energy consumption during exercise by building a real-time motion detection system. The development of sports health assessment systems, including the application of imaging techniques, is also analyzed. The experimental results in this article show that when the error threshold is set to 10%, the accuracy of the model is 85%, and the obtained results are ideal.

Motion detection and correction for carotid MRI using a markerless optical system

PurposeMotion related artifact is a challenge for MRI, especially when imaging regions like the carotid artery where complex motion (abrupt and bulk motion) may occur. This study aims to develop a non-contact motion detection and correction system for carotid MRI using a markerless optical tracking system. MethodsThe proposed markerless optical tracking system consisted of a cross-line laser, an MRI-compatible camera and plastic holders mounted inside the scanner bore. The neck motion of the subject can be captured by monitoring the change of the projected laser position in real-time. The system was used to correct both abrupt motion and bulk motion for carotid MRI. The abrupt motion (e.g. coughing) was compensated by discarding the corrupted k-space lines and re-estimating the missing lines using SPIRiT algorithm. The bulk motion was corrected by phase adjustment of k-space lines according to the measured 1D-translational bulk motion (along anterior-posterior direction) and optimized in-plane translation parameters. Ten volunteers underwent carotid MRI with real-time neck motion detection and retrospective motion correction. Artery sharpness, vessel wall thickness and overall image quality score were compared between the motion-corrupted image and motion-corrected images of different correction strategies. ResultsBoth the abrupt motion and the bulk motion during carotid scanning were successfully detected and corrected. The results of ten volunteers demonstrated significant improvement in carotid artery sharpness, vessel wall thickness measurement, and overall image quality score using the proposed markerless optical tracking system and motion correction strategies. ConclusionThe proposed markerless structured light based motion detection and correction system can sensitively detect both abrupt and bulk motion during carotid MR scans. By correcting for both abrupt and bulk motion, vessel wall delineation was improved in carotid MR images, which could potentially facilitate carotid plaque identification and atherosclerosis diagnosis in the future.

Wearable, washable and ultra-high environmental tolerant solid-liquid composite sensor based on IL@PU microcapsules

Tactile sensors are typically rigid restricting various natural motions and subjected to failure under pressure which compromise their conformability and durability. Here, we exploit the fluidity of ionic liquid (IL) which was encapsulated within a polyurea (PU) shell before being directly incorporated into flexible water-borne polyurethane (WPU) matrix. This approach not only ensured IL stability in the composite by preventing IL leakage but also low dielectric losses beneficial for low-power consumption. Such design yielded high sensitivity (0.083 kPa-1), fast response (40 ms), and excellent stability under cyclic pressure (3000 cycles). The sensor also demonstrated potential for robot gripping, e-skin and real time motion detection by accurately detecting pressure distribution and perceiving real time signals. Moreover, our sensor exhibited long-term sensing stability under complex environments, particularly upon repeated washing, which adequately addressed the poor washability of liquid-based sensors. As such, IL@PU/WPU capacitive sensors not only meet the low-power but washability requirements of wearable devices.

Real-Time Motion Detection Network Based on Single Linear Bottleneck and Pooling Compensation

Motion (change) detection is a basic preprocessing step in video processing, which has many application scenarios. One challenge is that deep learning-based methods require high computation power to improve their accuracy. In this paper, we introduce a novel semantic segmentation and lightweight-based network for motion detection, called Real-time Motion Detection Network Based on Single Linear Bottleneck and Pooling Compensation (MDNet-LBPC). In the feature extraction stage, the most computationally expensive CNN block is replaced with our single linear bottleneck operator to reduce the computational cost. During the decoder stage, our pooling compensation mechanism can supplement the useful motion detection information. To our best knowledge, this is the first work to use the lightweight operator to solve the motion detection task. We show that the acceleration performance of the single linear bottleneck is 5% higher than that of the linear bottleneck, which is more suitable for improving the efficiency of model inference. On the dataset CDNet2014, MDNet-LBPC increases the frames per second (FPS) metric by 123 compared to the suboptimal method FgSegNet_v2, ranking first in inference speed. Meanwhile, our MDNet-LBPC achieves 95.74% on the accuracy metric, which is comparable to the state-of-the-art methods.

Flexible and high-performance piezoresistive strain sensors based on multi-walled carbon nanotubes@polyurethane foam.

Flexible wearable pressure sensors have attracted special attention in the last 10 years due to their great potential in health monitoring, activity detection and as electronic skin. However, it is still a great challenge to develop high sensitivity, fast response, and good reliable stability through a simple and reproducible large-scale fabrication process. Here, we develop a simple and efficient method to fabricate three-dimensional (3D) light-weight piezoresistive sensing materials by coating multi-walled carbon nanotubes (MWCNTs) on the surface of polyurethane (PU) foam using a dip-spin coating process. The PU foam prepared with SEBS-g-MAH and polyether polyols has high elasticity and good stability in MWCNTs/DMF solution. Subsequently, a piezoresistive sensor was assembled with the prepared MWCNTs/PU composite foam and copper foil electrodes. The assembled pressure sensor has high sensitivity (62.37 kPa−1), a wide working range (0–172.6 kPa, 80% strain), a fast response time (less than 0.6 s), and reliable repeatability (≥2000 cycles). It has shown potential application in real-time human motion detection (e.g., arm bending, knee bending), and monitoring the brightness of LED lights.

Computer-Aided Interface Design for Real-Time Pupil Motion Detection and an Application for Physically Disabled Persons

In this study, a human-computer interface was created in C# so that individuals with physical mobility disabilities such as ALS can express their wishes. In this system created, pupil movements were analyzed and the patient's wishes were expressed both visually and audibly. In the system created for the tracking of the pupil, the face of the patient, which was detected by the camera, was detected autonomously by the system. An adaptive IR LED light source has been designed to illuminate the eye area of the user. Pupil motion detection was performed with the developed image processing algorithms. According to the movements of the detected pupil, commands were created on the user interface to express the wishes of the patient by using the location information of the patient. An application study was carried out by creating the prototype of the controlled patient bed with a 3D printer. At the end of this study, pupil motion detection was carried out using a camera without any contact with the user. With the algorithm created for pupil motion detection, it is ensured that the patient can express his wishes without the need for any movement other than eye movement. With this study, a uniquely developed algorithm that can be used in pupil tracking systems of individuals with physical movement disabilities such as ALS has been acquired.

Real-time motion detection with candidate masks and region growing for moving cameras

A fast and reliable motion detection method is proposed for moving cameras. Existing methods generally build background models and then apply background subtraction for moving pixels detection. In background modeling, statistical methods and/or features, such as edges, local binary patterns are used. Parameters of the proposed methods need to be updated adaptively for better performance. In recent studies, adaptive learning rates are used with main and candidate background models. Simple and adaptive thresholding methods are used for foreground detection in different studies. We build a statistical background model with hue–saturation–value color space and perform background subtraction with the contribution of optical flow vectors. Dense optical flow is applied between warped the background model and the current frame to estimate optical flow vectors. If a pixel has a larger magnitude, we set a weight value for each pixel in the background subtraction process. Then, we extract two candidate foreground masks and apply some postprocessing techniques to determine the final mask. Our proposed method works fast in real time, and the experimental results on two different datasets show that our approach has the highest performance compared with the methods in the literature.

Simple route to performance modulation of resistive strain sensor based on strain-engineered stretchable substrate with customized hard template

Despite recent remarkable advances in wearable strain sensors, it remains challenging to achieve a high sensitivity and high stretchability simultaneously within a single device. Herein, we present a simple yet universal route to geometric modulation of elastomeric substrates based on customized hard templates for systematically optimizing the sensing performance of stretchable strain sensors. The hard template is simply prepared by patterning a thin plastic sheet using a facile cut-patterning process and entirely embedded into elastomeric substrates to redistribute the surface strain upon stretching in a programmable manner. The proposed strain-engineered stretchable (SES) substrates with various designs of the hard templates are easily integrated with silver nanowire (AgNW)/elastomer composite sensory films and play a crucial role in achieving balanced sensing performance of the strain sensors. The AgNW/SES (AS) strain sensor exhibits a high stretchability (68%) and high mechanosensitivity (gauge factor of ∼4.5 at 0–25% and ∼33 at 25–68%) while exhibiting long-term performance stability (1000 stretching cycles at 30% strain). Owing to their excellent sensing performance and mechanical flexibility, the AS strain sensors are successfully used to monitor a wide range of strains caused by human activities during exercise, indicating the potential as practical wearable devices for real-time motion detection.

Design of upper limb prosthesis using real-time motion detection method based on EMG signal processing

Many people suffer from disability, caused by arm amputees and congenital disorder of the musculoskeletal system. An upper limb prosthesis can help disabled people to do their usual life activity. The aim of the paper is to develop upper limb prosthetic device controlled by myoelectric signals. At present the most complicated problem in upper limb prosthetics is connected with processing of neuromuscular signals for their use in control of the prosthesis. In modern prosthesis the intensity of muscle activity is extracted from the electromyographic signals. Prosthetic devices should ideally compensate for the loss of fine, coordinated movements of the hand, provide proprioceptive feedback, and have an esthetic exterior. From this point of view, identification of single finger movements seems very attractive. On the one hand it allows to restore functionality of amputated limb close to the healthy one. On the other hand existing results in the field of multifinger control require complicated computations. This leads to cost increase of the end-user device. To overcome this problem, we propose amplitude-based window recognition method with low computational complexity. The proposed solution can be implemented in real-time control using low cost Arduino nano microcontroller. A prototype of prosthetic hand with novel engineering solutions and proposed software is suggested. Experimental and statistical validation of identification scheme on a group of healthy people is considered. The proposed solution is tested in real time in autonomous mode. Experimental results for disabled man is provided. A discussion of the obtained results is given.