Multiple Human Tracking and Identification With Wireless Distributed Pyroelectric Sensor Systems

India’s defense drone ecosystem remains largely dependent on manual control and pre-programmed routines, restricting adaptability in rapidly evolving or GPS-denied environments. In this paper, we propose Drishti-AI Drone-based Reinforcement System for Intelligent Human Tracking and Identification using AI , a fully autonomous UAV surveillance framework that tightly integrates Reinforcement Learning (RL)–based navigation with real-time Deep Learning (DL)–driven human detection. For autonomous mobility, we introduce AeroNav-PPO, a Proximal Policy Optimization (PPO) model trained in a 3D AirSim environment to enable intelligent navigation and dynamic obstacle avoidance. For perception, we present YOLOv8-HawkEye, a customized object detection model capable of identifying humans with real-time coordinate mapping and automated alert generation. Together, these modules form a closed perception-action loop that enables end-to-end autonomous operation. The AeroNav-PPO agent demonstrated an average episode reward of 347.0 with consistent patrol performance across complex terrains, while YOLOv8-HawkEye achieved a precision of 95.6%, recall of 87.8%, and mAP@0.5 of 93.8%. Our results validate Drishti-AI as a promising step toward fully autonomous, mission-ready surveillance drones for next-generation defense applications.

There is an urgent need for intelligent home surveillance systems to provide home security, monitor health conditions, and detect emergencies of family members. One of the fundamental problems to realize the power of these intelligent services is how to detect, track, and identify people at home. Compared to RFID tags that need to be worn all the time, vision-based sensors provide a natural and nonintrusive solution. Observing that body appearance and body build, as well as face, provide valuable cues for human identification, we model and record multi-view faces, full-body colors and shapes of family members in an appearance database by using two Kinects located at a home's entrance. Then the Kinects and another set of color cameras installed in other parts of the house are used to detect, track, and identify people by matching the captured color images with the registered templates in the appearance database. People are detected and tracked by multisensor fusion (Kinects and color cameras) using a Kalman filter that can handle duplicate or partial measurements. People are identified by multimodal fusion (face, body appearance, and silhouette) using a track-based majority voting. Moreover, the appearance-based human detection, tracking, and identification modules can cooperate seamlessly and benefit from each other. Experimental results show the effectiveness of the human tracking across multiple sensors and human identification considering the information of multi-view faces, full-body clothes, and silhouettes. The proposed home surveillance system can be applied to domestic applications in digital home security and intelligent healthcare.

Identifying human presence in a visual surveillance system is crucial for variety of applications. Various tracking systems are also refined with a vision to detect human beings. However lesser resolution pictures make them a challenging one. So a stereo vision based human detection and tracking system is proposed for recognition of intruders in the human access controlled areas and can help in observing and inspecting illegal activities. In this depth range of the system is used in parameter estimation. The human presence is identified by skin detection where segmentation is done in HSV color space. Human tracking is a separate hardware system coupled through a serial port. For targeting servo motors are used, along a buzzer and a laser light for pointing the target. Here the presence of animals is also eliminated by a change in algorithm. The proposed implementation need only less protection and climate conditions are least influenced.

Forest leaf area index (LAI) is a key characteristic affecting a field canopy microclimate. In addition to traditional professional measuring instruments, smartphone-based methods have been used to measure forest LAI. However, when smartphone methods were used to measure conifer forest LAI, very different performances were obtained depending on whether the smartphone was held at the zenith angle or at a 57.5° angle. To further validate the potential of smartphone sensors for measuring conifer LAI and to find the limits of this method, this paper reports the results of a comparison of two smartphone methods with an LAI-2000 instrument. It is shown that the method with the smartphone oriented vertically upwards always produced better consistency in magnitude with LAI-2000. The bias of the LAI between the smartphone method and the LAI-2000 instrument was explained with regards to four aspects that can affect LAI: gap fraction; leaf projection ratio; sensor field of view (FOV); and viewing zenith angle (VZA). It was concluded that large FOV and large VZA cause the 57.5° method to overestimate the gap fraction and hence underestimate conifer LAI. For the vertically upward method, the bias caused by the overestimated gap fraction is compensated for by an underestimated leaf projection ratio.

Bare terrain surfaces have attracted little attention in albedo and remote sensing studies despite their large representation in desert and semi-arid regions of the world. It is the aim of this thesis to investigate the interaction of solar radiation with the Earth's bare surface structure in two stages. The first stage investigates the effect of surface structure on the incoming and outgoing flux using measurements of the Bidirectional Reflectance Distribution Function (BRDF) for various surface types. The second stage developes a methodology for the extraction of roughness information from the BRDF. Theories describing the effect of facets orientation and multiple reflections on the reflected radiance field are reviewed and discussed. Two major deficiencies are identified: firstly, there is a lack of radiometric data for rocky and stony terrain; secondly there is a lack of measurements which examine the contribution of multiple reflections to the reflected radiance. A methodology was developed to measure the contribution of secondary reflection (where the first reflection occurs outside the sensor field of view) to the upwelling radiance. In agreement with published models, results showed that the contribution can be high ( 30%) in certain geometrical configurations. However, unlike other model results, the role of anisotropic reflections via the particulate nature of the surface was found to be of prime importance.A simulation model was developed and it supported the experimental findings. A study of the BRDF in relation to surface properties was conducted in arid land near Fowlers Gap Research Station, New South Wales. New apparatus was developed to take accurate Hemispherical Directions Radiance Measurements (HDRM). A digitizer for three dimensional in situ roughness measurements was also developed. More than 100 hemispherical data sets were collected for various illumination conditions and surface types: dunes, desert stony pavements and rocky terrain slopes. In general it was found that most of the surfaces exhibited an anisotropic reflection, combining a major component of backscattering with a weaker component of forward scattering. The BRDF of the different surface types in relation to their roughness properties as determined by the field digitizer is then examined. The main hypothesis in this research concerns the inverse process of determining the microstructure of the surface from the directional distribution of reflected radiance. It states that given several sets of directional reflected radiance measurements, it should be possible to derive the roughness characteristics of the surface. The question whether the BRDF has a one-to-one correspondence with the surface microstructure is then addressed. A technique was developed to simulate a wide range of microelements and their BRDF. Results from the simulation show a significant number of cases of equifinality in which a variety of microstructures exhibit the same BRDF. Analysis of these cases suggests that there are many distinctively different combinations of structural properties which can balance the effect of structure on the reflected radiance field. A comparison of field measurements with the simulated cases confirms that BRDF equifinality must be considered in remote sensing applications where there is a need to derive surface properties such as roughness, microstructure and texture from satellite data. Analysis of the microstructures which exhibited equifinality revealed that they have similarity in their roughness properties. Two parameters are then introduced for characterizing the surfaces' roughness in relation to their reflectance properties. On the basis of the simulation data a method is derived for determining the roughness parameters from reflectance. data in certain viewing angles. The assessment of the results showed a moderate to high accuracy which varied with the sun zenith angle.

Multiple human detection and tracking is a complicated task in real scenarios. We present in this article a robust approach for multiple human detection, tracking and identification. For human detection, an improved HOG human detector is used. In multiple human tracking, serving to inter-frame accordance, it is essential to generate distinctive signatures for each person. As global appearance description can be sensitive to illumination and intra-class variation, we therefore incorporate a local invariant feature (SIFT features) to increase robustness of matching. Both color-histogram and SIFT features are used in our approach. Experimental works demonstrate its effectiveness and robustness.

This paper proposes a human motion tracking approach for a daily life surveillance in a distributed wireless sensor network using ultrasonic range sensors. Because the human target often moves with high nonlinearity, the proposed approach applies the unscented Kalman filter (UKF) technique. A novel sensor node selection scheme at each time step considering both the tracking accuracy and the energy cost is presented. Experimental results in a real human motion tracking system show that the proposed approach can perform better tracking accuracy compared to the most recent human motion tracking scheme in the real testbed implementation.

There exists a well-known visual illusion with respect to color propagation. That is, a human subject confuses a color in the subject's peripheral field of view (FOV) as another color in the central FOV (with a shape of circular disk) spreads into the peripheral FOV or as a color in the peripheral FOV erodes another color in the central FOV (also with a shape of circular disk) when he/she keeps gazing at a specific color visual stimulus in his/her central FOV for more than several seconds. In this paper, the authors experiment this illusion using multiple naive subjects in conditions of the visual stimuli as the central or peripheral colors and the disk size change. This paper has proposed a rate of propagation as a criterion and has analyzed and discussed the illusion using it.

This paper proposes a human motion tracking approach for daily life surveillance in a distributed wireless sensor network using ultrasonic range sensors.Because the human target often moves with high non linearity, the proposed approach applies the unscented Kalman filter (UKF) technique. Experimental results in a real human motion tracking system show that the proposed approach can perform better tracking accuracy compared to the most recent human motion tracking scheme in the real test-bed implementation.

Human tracking in indoor environment plays an important role in intelligent housing system that enables the smart appliances to provide fine-grained services with the information of users' walking trajectories. This paper presents a device-free human tracking system only using existing commercial WiFi supported devices and smart appliances. We consider that a human walking trajectory consists of a series of moving behaviors and we can determine the trajectory by detect those behaviors. Those behaviors can be sensed according to their influence on the signals of neighboring WiFi devices (we call these devices Check Points). A machine learning method is used to train a classifier to identify the above behaviors. Furthermore, an uniform trace recording format consisting of the moving behaviors series, is designed for thewalking trajectories comparison. By calculating the similarity between the measured human trace and stored trace profiles, we can determine the specific trajectory. Our experimental evaluation in three different scenarios shows that our approach can achieve over 95% average accuracy on moving behaviors identification and over 90% average accuracy on trace determination.

Object detection and human tracking are vital for pairing computer vision to a quadrotor. One application for this is monitoring traffic by either classifying vehicles or tracking people through the crowd. This was proven true by the developed system, garnering a detection rate of 77% for various vehicles in the Philippines, and showing the ability to track people on a dual camera system albeit as a proof-of-concept only. Though this can be a potentially huge field for digital image processing, there is still a challenge of creating a fast and responsive application through wireless communication. This study presented a quantitative data when approaching a quadcopter equipped with dual camera system streamed through WiFi connection.

In this paper, we show the existence of human radio biometrics and present a human identification system that can discriminate individuals even through the walls in a non-line-of-sight condition. Using commodity Wi-Fi devices, the proposed system captures the channel state information (CSI) and extracts human radio biometric information from Wi-Fi signals using the time-reversal (TR) technique. By leveraging the fact that broadband wireless CSI has a significant number of multipaths, which can be altered by human body interferences, the proposed system can recognize individuals in the TR domain without line-of-sight radio. We built a prototype of the TR human identification system using standard Wi-Fi chipsets with $3 \times 3$ multi-in multi-out (MIMO) transmission. The performance of the proposed system is evaluated and validated through multiple experiments. In general, the TR human identification system achieves an accuracy of 98.78% for identifying about a dozen of individuals using a single transmitter and receiver pair. Thanks to the ubiquitousness of Wi-Fi, the proposed system shows the promise for future low-cost low-complexity reliable human identification applications based on radio biometrics.

The autonomous navigation capabilities of mobile robots is a social and technological issue.Many potential applications add to the importance of human following technology.Some of the applications include museum guide robots and service robots at shopping center.In this paper,we propose the detection and tracking schemes for human legs by the use of a camera.The robust tracking of humans is achieved by exploiting a human walking model.The leg detection and tracking schemes are realized by the combined application of support vector data description algorithm and a wheeled mobile robot.The proposed scheme is successfully verified in real time environments. Index term: Human following, Human-robot interaction,Leg detection,Mobile robot navigation,SVDD algorithm.

Multiple human tracking in high-density crowds

Visual surveillance in crowded scenes, especially for humans, has recently been one of the most active research topics in machine vision because of its applications such as deter and response to crime, suspicious activities, terrorism or human behavior recognition. One of the most important problems in multiple human tracking is the occlusion problem. When the number of humans has an occlusion with each other or the background, the tracker should track them correctly. In this paper, we use particle swarm optimization (PSO) as a tracker, in addition to the Kalman filter and some other mathematical equations to solve the occlusion problem which the occlusion can be partially or completely. Experimental results on several real videos sequences from different conditions have shown the effectiveness of our approach.