Autonomous Surveillance System Research Articles

IOT based Autonomous Location Surveillance System Using PNT Services

The entire set of interconnected devices as well as the technology enabling communication between the devices and the cloud. This article presents an innovative Internet of Things (IOT)based autonomous location monitoring system that is made possible by Positioning, Navigation, and Timing (PNT) services. The system allows for real-time tracking and surveillance of objects or persons by combining Internet of Things sensors and communication modules with PNT technologies like GPS, Galileo, or GLONASS. The technology uses advanced machine learning techniques and algorithms to automatically identify and evaluate anomalies in the monitored area. It then swiftly reports these findings to the relevant authorities.PNT services are seamlessly linked to ensure accurate and reliable location, even in challenging Environment. In addition to being adaptable, scalable, and compatible with existing infrastructure, the Technology has a wide range of applications, including border security, asset protection, and perimeter monitoring. This work advances the possibilities of autonomous surveillance systems. In depth features provided by the research include mobile number identification (subject to legal and regulatory constraints), real-time location visualization, and centralized vehicle data management for enhanced fleet management, security, and operational effectiveness The development of sophisticated solutions that make use of precision navigation and timing (PNT) and the internet of things (IOT) has been spurred by the growing need for effective location based surveillance systems. Edge computing units, a central control unit and a monitoring and control user interface are important parts of the system. Data is processed locally with edge computing, which lowers latency and improves response times. to create a self-contained location monitoring system using precise PNT services and IOT technology. Keywords: IOT, Real-Time Tracking, Vehicle Management, Python Flask, Mobile Number Tracking, Data Fetching

Deep Surveillance System

This study has been undertaken to investigate and implement multiple detection systems into a single surveillance system and check whether the input videos may comprise and capture a variety of realistic anomalies or not. In this paper, we propose to learn various anomalies by exploiting both normal and anomalous videos and implemented it to new model. Real time object detection is a vast, vibrant and sophisticated area of computer vision aimed towards object identification and recognition. Object detection detects the semantic objects of a class objects using Open source Computer Vision, which is a library of programming functions mainly trained towards real time computer vision in digital images and videos. The main aim behind this real time object detection is to help the peoples to overcome their difficulty. Real time object detection finds its uses in the areas like tracking objects, video surveillance, pedestrian detection, people counting, self-driving cars, face detection, tracking in sports and many more. This is achieved using Convolution, Probabilistic Neural Networks, etc. which are a representative tool of Deep learning. This project acts as an aiding tool for peoples who wants to take care of everything inside, outside, and around their house just for their full security expectations. Surveillance is a must for small houses to large-scale industries as they fulfil our safety aspects because theft and burglary have always been a problem. By combining this Surveillance idea to IoT and some Machine Learning stuff this will be a major product. The proposed project is a single autonomous surveillance system, based on analysis and detection technology. The proposed system is capable of monitoring all actions at once and alerts the concerned officials immediately and precisely.

An Intelligent Bio-Inspired Autonomous Surveillance System Using Underwater Sensor Networks.

Energy efficiency is important for underwater sensor networks. Designing such networks is challenging due to underwater environmental traits that hinder network lifespan extension. Unlike terrestrial protocols, underwater settings require novel protocols due to slower signal propagation. To enhance energy efficiency in underwater sensor networks, ongoing research concentrates on developing innovative solutions. Thus, in this paper, an intelligent bio-inspired autonomous surveillance system using underwater sensor networks is proposed as an efficient method for data communication. The tunicate swarm algorithm is used for the election of the cluster heads by considering different parameters such as energy, distance, and density. Each layer has several clusters, each of which is led by a cluster head that continuously rotates in response to the fitness values of the SNs using the tunicate swarm algorithm. The performance of the proposed protocol is compared with existing methods such as EE-LHCR, EE-DBR, and DBR, and results show the network's lifespan is improved by the proposed work. Due to the effective fitness parameters during cluster head elections, our suggested protocol may more effectively achieve energy balance, resulting in a longer network lifespan.

Multispectral Invisible Coating: Laminated Visible-Thermal Physical Attack against Multispectral Object Detectors Using Transparent Low-E Films

Multispectral object detection plays a vital role in safety-critical vision systems that require an around-the-clock operation and encounter dynamic real-world situations(e.g., self-driving cars and autonomous surveillance systems). Despite its crucial competence in safety-related applications, its security against physical attacks is severely understudied. We investigate the vulnerability of multispectral detectors against physical attacks by proposing a new physical method: Multispectral Invisible Coating. Utilizing transparent Low-e films, we realize a laminated visible-thermal physical attack by attaching Low-e films over a visible attack printing. Moreover, we apply our physical method to manufacture a Multispectral Invisible Suit that hides persons from the multiple view angles of Multispectral detectors. To simulate our attack under various surveillance scenes, we constructed a large-scale multispectral pedestrian dataset which we will release in public. Extensive experiments show that our proposed method effectively attacks the state-of-the-art multispectral detector both in the digital space and the physical world.

Pedestrian Detection Using MB-CSP Model and Boosted Identity Aware Non-Maximum Suppression

Pedestrian detection is an important task in autonomous surveillance systems. Despite the rapid progress in pedestrian detection field, detecting occluded pedestrians remains a challenging task due to the great variations in occluded pedestrians appearance and the drastic loss of pedestrian information in some severe cases. In this paper, we tackle the occlusion problem by proposing a multi-branch pedestrian detection model based on center and scale prediction framework. The proposed model employs features extracted from full pedestrian’s body as well as its upper, middle, and lower body parts using four detection branches. This multi-branch approach ensures that data representing the true pedestrian appearances, whether they are partially or completely visible, can dominate the final decision-making, minimizing the interference of non-pedestrian data in the detection. Furthermore, to implement the proposed model, the visibility of different pedestrian parts is appropriately annotated, which facilitates the training process. The final decision is made based on the four MB-CSP branches outputs, using a proposed fusing method, named Boosted Identity Aware-Non Maximum Suppression. On heavy occlusion settings, the proposed model resulted in the miss rates of 27.83%, 47.29% and 33.3% for Caltech-USA, Citypersons and EuroCity Persons datasets, respectively.

An autonomous decision-making framework for gait recognition systems against adversarial attack using reinforcement learning

Gait identification based on Deep Learning (DL) techniques has recently emerged as biometric technology for surveillance. We leveraged the vulnerabilities and decision-making abilities of the DL model in gait-based autonomous surveillance systems when attackers have no access to underlying model gradients/structures using a patch-based black-box adversarial attack with Reinforcement Learning (RL). These automated surveillance systems are secured, blocking the attacker’s access. Therefore, the attack can be conducted in an RL framework where the agent’s goal is determining the optimal image location, causing the model to perform incorrectly when perturbed with random pixels. Furthermore, the proposed adversarial attack presents encouraging results (maximum success rate = 77.59%). Researchers should explore system resilience scenarios (e.g., when attackers have no system access) before using these models in surveillance applications.

Design of Multimodal Sensor Module for Outdoor Robot Surveillance System

Recent studies on surveillance systems have employed various sensors to recognize and understand outdoor environments. In a complex outdoor environment, useful sensor data obtained under all weather conditions, during the night and day, can be utilized for application to robots in a real environment. Autonomous surveillance systems require a sensor system that can acquire various types of sensor data and can be easily mounted on fixed and mobile agents. In this study, we propose a method for modularizing multiple vision and sound sensors into one system, extracting data synchronized with 3D LiDAR sensors, and matching them to obtain data from various outdoor environments. The proposed multimodal sensor module can acquire six types of images: RGB, thermal, night vision, depth, fast RGB, and IR. Using the proposed module with a 3D LiDAR sensor, multimodal sensor data were obtained from fixed and mobile agents and tested for more than four years. To further prove its usefulness, this module was used as a monitoring system for six months to monitor anomalies occurring at a given site. In the future, we expect that the data obtained from multimodal sensor systems can be used for various applications in outdoor environments.

A Lightweight Efficient Person Re-Identification Method Based on Multi-Attribute Feature Generation

Person re-identification (re-ID) technology has attracted extensive interests in critical applications of daily lives, such as autonomous surveillance systems and intelligent control. However, light-weight and efficient person re-ID solutions are rare because the limited computing resources cannot guarantee accuracy and efficiency in detecting person features, which inevitably results in performance bottleneck in real-time applications. Aiming at this research challenge, this study developed a lightweight framework for generation of the person multi-attribute feature. The framework mainly consists of three sub-networks each conforming to a convolutional neural network architecture: (1) the accessory attribute network (a-ANet) grasps the person ornament information for an accessory descriptor; (2) the body attribute network (b-ANet) captures the person region structure for a body descriptor; and (3) the color attribute network (c-ANet) forms the color descriptor to maintain the consistency of the color of the person(s). Inspired by the human visual processing mechanism, these descriptors (each “descriptor” corresponds to the attribute of an individual person) are integrated via a tree-based feature-selection method to construct a global “feature”, i.e., a multi-attribute descriptor of the person serving as the key to identify the person. Distance learning is then exploited to measure the person similarity for the final person re-identification. Experiments have been performed on four public datasets to evaluate the proposed framework: CUHK-01, CUHK-03, Market-1501, and VIPeR. The results indicate that (1) the multi-attribute feature outperforms most of the existing feature-representation methods by 5–10% at rank@1 in terms of the cumulative matching curve criterion; and (2) the time required for recognition is as low as O(n) for real-time person re-ID applications.

Known and Unknown Transboundary Infectious Diseases as Hybrid Threats.

The pathogenicity, transmissibility, environmental stability, and potential for genetic manipulation make microbes hybrid threats that could blur the distinction between peace and war. These agents can fall below the detection, attribution, and response capabilities of a nation and seriously affect their health, trade, and security. A framework that could enhance horizon scanning regarding the potential risk of microbes used as hybrid threats requires not only accurately discriminating known and unknown pathogens but building novel scenarios to deploy mitigation strategies. This demands the transition of analyst-based biosurveillance tracking a narrow set of pathogens toward an autonomous biosurveillance enterprise capable of processing vast data streams beyond human cognitive capabilities. Autonomous surveillance systems must gather, integrate, analyze, and visualize billions of data points from different and unrelated sources. Machine learning and artificial intelligence algorithms can contextualize capability information for different stakeholders at different levels of resolution: strategic and tactical. This document provides a discussion of the use of microorganisms as hybrid threats and considerations to quantitatively estimate their risk to ensure societal awareness, preparedness, mitigation, and resilience.

Design and Implementation of an Intelligent Autonomous Surveillance System for Indoor Environments

This paper aims to develop an intelligent autonomous surveillance system for the safety surveillance of indoor environments with the integration of techniques such as sensory information fusion, internet of things (IoT), and artificial intelligence (AI). We have developed the following four subsystems to implement the intelligent autonomous surveillance system: (1) an autonomous surveillance vehicle (ASV) to be placed on the track to detect environmental sensory information in indoor environments (such as environmental temperature, flame, CO concentration, and liquefied petroleum gas (LPG) concentration) and the movement information of the ASV (such as position coordinates and movement speed); (2) an intelligent fire detection algorithm to be used for identification of disaster statuses in indoor environments; (3) a visible human-machine interface to instantaneously display the environmental sensory information and ASV movement information, and show the environmental disaster information (such as disaster statuses, disaster images, image capture times, and disaster positions); (4) a remote server composed of a database server, file servers, a web server, and responsive web pages to store and display the recorded environmental sensory information, ASV movement information, and environmental disaster information. Furthermore, a 3D experimental track testbed was constructed to verify the effectiveness and feasibility of the intelligent autonomous surveillance system. Our experimental results have successfully validated that the intelligent autonomous surveillance system can detect disaster events in a variety of conditions.

Optimizing Radio Coverage Based on Cellular Automata

Autonomous surveillance systems based on wireless sensor networks have brought many benefits for understanding, protecting, and preserving biodiversity thanks to the latest sensor and telecommunication technologies. For example, in archipelagoes with many rocks of various shapes and elevations interleaved with water, it is hard to deploy wireless sensing systems for covering all these given areas. In these sensing systems, coverages are defined as where information is accessible. In this article, a new approach is proposed, adopting cellular automata and massively parallel processing on GPUs. This work relates to the development of parallel algorithms and CAD tools to optimize coverage oriented to efficient deployment of wide-range wireless networks for various purposes such as environmental surveillance, early warning systems for natural hazards and risks, taking into account turbulence in topology. Some experiments on radio coverage were done in different complex terrain areas given positive results in terms of performance and functional requirements.

합성곱 신경망 기반의 헬기 기종 분류 모형 연구

In various surveillance systems, it is difficult to identify objects by relying on the naked eye. As the number of troops and the length of military service has been reduced in the Republic of Korea Army, there is a growing need for autonomous surveillance systems that could replace soldiers in the field of military surveillance operations. Thus, in this paper, we used binary classification based on a CNN (Convolutional Neural Network), which is a deep learning algorithm, to develop an autonomous model that classifies types of helicopters among the military weapon systems. We then evaluated the model’s performance. Consequently, the identification model demonstrates 98.9%, 99.4%, 98.4%, and 98.9% accuracy, precision, recall, and F-measure, respectively. In addition, we analyzed the feature map on the convolution layers of the identification model to check which area of imagery is highly weighted. In general, the rotary shaft of the rotating wing, wheels, and air-intake in both mobile and attack helicopters play a major role in the performance of the identification model.

Multi-frame feature-fusion-based model for violence detection

Human behavior detection is essential for public safety and monitoring. However, in human-based surveillance systems, it requires continuous human attention and observation, which is a difficult task. Detection of violent human behavior using autonomous surveillance systems is of critical importance for uninterrupted video surveillance. In this paper, we propose a novel method to detect fights or violent actions based on learning both the spatial and temporal features from equally spaced sequential frames of a video. Multi-level features for two sequential frames, extracted from the convolutional neural network’s top and bottom layers, are combined using the proposed feature fusion method to take into account the motion information. We also proposed Wide-Dense Residual Block to learn these combined spatial features from the two input frames. These learned features are then concatenated and fed to long short-term memory units for capturing temporal dependencies. The feature fusion method and use of additional wide-dense residual blocks enable the network to learn combined features from the input frames effectively and yields better accuracy results. Experimental results evaluated on four publicly available datasets: HockeyFight, Movies, ViolentFlow and BEHAVE show the superior performance of the proposed model in comparison with the state-of-the-art methods.

Change Detection in Aerial Images Using Three-Dimensional Feature Maps

Interest in aerial image analysis has increased owing to recent developments in and availability of aerial imaging technologies, like unmanned aerial vehicles (UAVs), as well as a growing need for autonomous surveillance systems. Variant illumination, intensity noise, and different viewpoints are among the main challenges to overcome in order to determine changes in aerial images. In this paper, we present a robust method for change detection in aerial images. To accomplish this, the method extracts three-dimensional (3D) features for segmentation of objects above a defined reference surface at each instant. The acquired 3D feature maps, with two measurements, are then used to determine changes in a scene over time. In addition, the important parameters that affect measurement, such as the camera’s sampling rate, image resolution, the height of the drone, and the pixel’s height information, are investigated through a mathematical model. To exhibit its applicability, the proposed method has been evaluated on aerial images of various real-world locations and the results are promising. The performance indicates the robustness of the method in addressing the problems of conventional change detection methods, such as intensity differences and shadows.

Guest Editorial: Artificial Intelligence Can Reduce ESP Failures

Guest editorial Electrical submersible pump (ESP) technology predominates the artificial lift options available to onshore and off-shore operators for maximizing production from medium-to-deep reservoirs. Although designed, engineered, and built to withstand extreme subsurface conditions—corrosive liquids, scalding temperatures, and intense pressures—ESPs can and do fail without warning, often despite having monitoring systems in place. These failures disrupt production and operator cash flows. Ultimately, the costs of replacing an ESP and its associated production losses can be enormous. But the risk of ESP failures can be greatly reduced with the right combination of advanced technologies, such as applying artificial intelligence (AI) combined with a secure, cloud-based Internet of Things (IoT) autonomous surveillance system. This provides operators with an early-warning system of ESP performance degradation in the form of a probabilistic, predictive maintenance model. With it, they can make better-informed decisions about the root causes of performance anomalies as well as how to mitigate, remediate, or manage them until the well’s next planned shutdown. In one pilot deployment of this application across a fleet of 30 ESPs, the failure of one was accurately predicted 12 days before it occurred. Monitoring of ESP Fleets Today, ESPs are deployed into reservoirs with sufficient sensors and instrumentation to enable continuous alarm-limit monitoring by technicians, who also keep a close watch on above-ground controls and motor drives. A distributed control system, often a supervisory control and data acquisition (SCADA) system, transmits an ESP’s operating data, which is recorded in a historian database. The data can then be used later for diagnostics. In practice, this approach is most often reactive, not proactive. That’s because conventional tools lack the ability to predict an ESP failure. In contrast, consider the use of a more predictive monitoring model that can employ AI-based pattern recognition. This capability not only can identify ESP behavioral anomalies but also can provide actionable intelligence about their root causes—and, importantly, the probability of an ESP failure based on the data-fueled refinement of the AI algorithms (i.e., machine learning). With this knowledge, an operator’s technical staff can better decide a proper course of action should they get an early warning about ESP performance issues. They can also be freed from having to constantly monitor ESP systems for alarm notifications and implement corrective actions. One benefit of this is that their time can be invested in more value-adding production activities. As an implementation of AI, machine learning (ML) is based on the use of deep learning via neural networks. To implement it as an ESP predictive monitoring model, data scientists use ESP historical data to create a training data set. The latter then “teaches” the software-coded neural network all the highly dynamic, relational behaviors and interactions between the many variables within a process, as defined by an ESP’s various operating KPIs.

Ageing-in-place with the use of ambient intelligence technology: Perspectives of older users

IntroductionAmbient intelligence technologies are a means to support ageing-in-place by monitoring clients in the home. In this study, monitoring is applied for the purpose of raising an alarm in an emergency situation, and thereby, providing an increased sense of safety and security. Apart from these technological solutions, there are numerous environmental interventions in the home environment that can support people to age-in-place. The aim of this study was to investigate the needs and motives, related to ageing-in-place, of the respondents receiving ambient intelligence technologies, and to investigate whether, and how, these technologies contributed to aspects of ageing-in-place. MethodologyThis paper presents the results of a qualitative study comprised of interviews and observations of technology and environmental interventions in the home environment among 18 community-dwelling older adults with a complex demand for care. These respondents had a prototype of the Unattended Autonomous Surveillance system, an example of ambient intelligence technology, installed in their homes as a means to age-in-place. The UAS-system offers a large range of functionalities, including mobility monitoring, voice response, fire detection, as well as wandering detection and prevention, which can be installed in different configurations. ResultsThe respondents had various motives to use ambient intelligence technologies to support ageing-in-place. The most prominent reason was to improve the sense of safety and security, in particular, in case of fall incidents, when people were afraid not to be able to use their existing emergency response systems. The ambient intelligence technologies were initially seen as a welcome addition to strategies already adopted by the respondents, including a variety of home modifications and assistive devices. The systems tested increased the sense of safety and security and helped to postpone institutionalisation. Respondents came up with a set of specifications in terms of the operation and the design of the technology. False alarms were also regarded as a sign that the ambient intelligence technology is functioning. Moreover, a good integration of the new technologies in the provision of health care is indispensable, and installation should be done in an acceptable and unobtrusive manner. Conclusions and implicationsAmbient intelligence technologies can contribute to an increased safety and security at home. The technologies alone offer no all encompassing solution as home care and additional environmental interventions are still needed to support ageing-in-place. Results of the study are used to further improve the ambient intelligence technologies and their implementation.

Systems and algorithms for autonomous and scalable crowd surveillance using robotic PTZ cameras assisted by a wide-angle camera

We report an autonomous surveillance system with multiple pan-tilt-zoom (PTZ) cameras assisted by a fixed wide-angle camera. The wide-angle camera provides large but low resolution coverage and detects and tracks all moving objects in the scene. Based on the output of the wide-angle camera, the system generates spatiotemporal observation requests for each moving object, which are candidates for close-up views using PTZ cameras. Due to the fact that there are usually much more objects than the number of PTZ cameras, the system first assigns a subset of the requests/objects to each PTZ camera. The PTZ cameras then select the parameter settings that best satisfy the assigned competing requests to provide high resolution views of the moving objects. We propose an approximation algorithm to solve the request assignment and the camera parameter selection problems in real time. The effectiveness of the proposed system is validated in both simulation and physical experiment. In comparison with an existing work using simulation, it shows that in heavy traffic scenarios, our algorithm increases the number of observed objects by over 210%.

Survey and analysis of multimodal sensor planning and integration for wide area surveillance

Although sensor planning in computer vision has been a subject of research for over two decades, a vast majority of the research seems to concentrate on two particular applications in a rather limited context of laboratory and industrial workbenches, namely 3D object reconstruction and robotic arm manipulation. Recently, increasing interest is engaged in research to come up with solutions that provide wide-area autonomous surveillance systems for object characterization and situation awareness, which involves portable, wireless, and/or Internet connected radar, digital video, and/or infrared sensors. The prominent research problems associated with multisensor integration for wide-area surveillance are modality selection, sensor planning, data fusion, and data exchange (communication) among multiple sensors. Thus, the requirements and constraints to be addressed include far-field view, wide coverage, high resolution, cooperative sensors, adaptive sensing modalities, dynamic objects, and uncontrolled environments. This article summarizes a new survey and analysis conducted in light of these challenging requirements and constraints. It involves techniques and strategies from work done in the areas of sensor fusion, sensor networks, smart sensing, Geographic Information Systems (GIS), photogrammetry, and other intelligent systems where finding optimal solutions to the placement and deployment of multimodal sensors covering a wide area is important. While techniques covered in this survey are applicable to many wide-area environments such as traffic monitoring, airport terminal surveillance, parking lot surveillance, etc., our examples will be drawn mainly from such applications as harbor security and long-range face recognition.

Unattended autonomous surveillance in community-dwelling older adults: a field study

Home automation that allows for telecare services is increasingly becoming a tool to help older adults live independently and to improve perceived safety and security. The number of older adults receiving professional care, in relation to housing, on a daily basis is not very large. Only 15% receives home care, 5% lives in a care home, and about 2.5% resides in a nursing home. The majority of older adults live in the community. The Unattended Autonomous Surveillance system by TNO Defense is an integrated system that combines many functionalities for community-dwelling (older) adults, who are entitled to receiving nursing home care based on official assessments. The technology is implemented among people in the towns of Baarn and Soest in the centre of the Netherlands. The UAS system aims to support Ageing-in-Place and delaying the demand for expensive institutional care. Besides the benefits for the care recipient, informal or family carers are supported in care through the technology installed as well. Professional carers, for instance, home care, can benefit from the increased self care capabilities of the care recipient. In cases of emergency, i.e., when alarms are activated, people in the care centre can access the home via a camera. The aim is to study the perceptions of independent living, the role and quality of care received, and how people think technology can support them in their daily lives. This is the first round of interviewing on a total of three rounds. Methods In order to investigate the needs of the users, phenomenological qualitative research is carried out among a group of 30 independently living older adults (some with mild psychogeriatric health problems) and their (family) carers, using semi-structured questionnaires on home care received, demand for care, use and need of assistive technologies and perceived safety and security. The questionnaires were based on earlier work by Bijsterveld1 and Demeris et al.2. The first part of the study, performed between May and September 2007, included 14 subjects. The transcripts were analysed using the MAXQDA program. First, each transcript was read in its entirety. Then, they were read a second time to develop codes that were grouped into themes consistent with the interviews, which emerged from the narratives and the interview guides. To be considered a major theme, the code had to have appeared in more than 25% of the narratives and more than once in each of the narratives. Third, quotes that summarised the essence of each person’s subjective experience were recorded. Finally, a master list of themes from each interview was developed to allow for easy cross-interview examination. Results and discussion Preliminary results showed a positive attitude of older adults towards the system as a means to provide additional telecare and to increase perceived security in their surroundings. The fact that professional carers are immediately available after an emergency call, for instance via video communication, eases their feelings of insecurity. Family carers were more enthusiast about the system than many older adults, because the UAS system that is always present and vigilant takes away a part of the care burden. The over-time contribution of the UAS system to independence is to be studied.

Distributed surveillance and reconnaissance using multiple autonomous ATVs: CyberScout

The objective of the CyberScout project is to develop an autonomous surveillance and reconnaissance system using a network of all-terrain vehicles. We focus on two facets of this system: 1) vision for surveillance and 2) autonomous navigation and dynamic path planning. In the area of vision-based surveillance, we have developed robust, efficient algorithms to detect, classify, and track moving objects of interest (person, people, or vehicle) with a static camera. Adaptation through feedback from the classifier and tracker allow the detector to use grayscale imagery, but perform as well as prior color-based detectors. We have extended the detector using scene mosaicing to detect and index moving objects when the camera is panning or tilting. The classification algorithm performs well with coarse inputs, has unparalleled rejection capabilities, and can flag novel moving objects. The tracking algorithm achieves highly accurate (96%) frame-to-frame correspondence for multiple moving objects in cluttered scenes by determining the discriminant relevance of object features. We have also developed a novel mission coordination architecture, CPAD (Checkpoint/Priority/Action Database), which performs path planning via checkpoint and dynamic priority assignment, using statistical estimates of the environment's motion structure. The motion structure is used to make both preplanning and reactive behaviors more efficient by applying global context. This approach is more computationally efficient than centralized approaches and exploits robot cooperation in dynamic environments better than decoupled approaches.