Umwelt and Melody: The Inter-Species Dynamics of Search and Rescue Dog Teams

Salivary cortisol levels in search and rescue (SAR) dogs under rescue examination conditions

Quantifying Search Dog Effectiveness in a Terrestrial Search and Rescue Environment

Professional search and rescue (SAR) dogs, which are members of urban search and rescue teams with the help of their higher sense organs with rigorous training, are very helpful in finding buried or missing persons in disasters. In these environments where chaos and disorder prevail, it becomes inevitable for them to face very dangerous and risky situations. As a result of a disaster caused by chemical, biological, radiological and nuclear (CBRN) accidents, dangers such as chemical leaks, pathogenic microorganisms, toxins, vectors, and radioactive and nuclear materials in the environment are among the forgotten or neglected facts that SAR dogs affect as well as affect humanity. Working with little or no personal protective equipment during search and rescue interventions makes them completely vulnerable to these hazards. In the limited resources in the literature on CBRN risks and dangers that search and rescue dogs working in disaster areas may encounter, SAR dogs are exposed to many chemicals and toxic agents during these studies, as well as biological hazards such as protozoal or coliform bacterial organisms, and radiological hazards such as the risk of ingesting radioactive materials and breathing dust. their arrival has been determined. With this study, it was aimed to emphasize the dangers faced by SAR dogs and to emphasize what has been done and what should be done to reduce the possible risks. As a result, necessary precautions should be taken to prevent and/or reduce these possible exposures of SAR dogs, and further studies should be carried out for appropriate standard procedures for appropriate rehabilitation and decontamination.

A cyber-enhanced rescue canine (CRC) suit was developed to collect and share information such as real-time video, location of the search and rescue (SAR) dog, and behavior analysis, which are important in rescue operation and help enhance the search and rescue performance. Although the CRC suits successfully served its purposes in aiding the rescue team in field tests, some issues regarding the CRC suit were identified: overheating of the CRC suit and change in suit inclination on the back of the SAR dog. These issues prevent the full utilization of the CRC suit and thus needed to be improved. Here, we propose a lightweight CRC suit with heat protection and anti-slip countermeasures as an improvement over the original CRC suit. With the countermeasures for the Wi-Fi dongle and the camera heating issues, the CRC suit can now be operated at temperatures over 40 °C, whereas the CRC suit inclination problem on the dog was solved by adjusting the length of the chest belt. Further, the proposed CRC suit is lighter (1.2 kg, 18.3% decrease from the old suit in weight) and smaller, which helps reduce the burden on the SAR dog. Furthermore, the performance of the CRC suit was verified by employing the suit in actual scenarios; the CRC suits were provided to SAR dog teams in the eastern and western areas of Japan for training and preparing for actual disasters in the future, respectively.

Search and Rescue (SaR) dogs are important assets in the hands of first responders, as they have the ability to locate the victim even in cases where the vision and or the sound is limited, due to their inherent talents in olfactory and auditory senses. In this work, we propose a deep-learning-assisted implementation incorporating a wearable device, a base station, a mobile application, and a cloud-based infrastructure that can first monitor in real-time the activity, the audio signals, and the location of a SaR dog, and second, recognize and alert the rescuing team whenever the SaR dog spots a victim. For this purpose, we employed deep Convolutional Neural Networks (CNN) both for the activity recognition and the sound classification, which are trained using data from inertial sensors, such as 3-axial accelerometer and gyroscope and from the wearable’s microphone, respectively. The developed deep learning models were deployed on the wearable device, while the overall proposed implementation was validated in two discrete search and rescue scenarios, managing to successfully spot the victim (i.e., obtained F1-score more than 99%) and inform the rescue team in real-time for both scenarios.

Sidecountry Rescue—Who Should Respond to Ski Resort Out-of-Bounds Rescues?

Search and rescue (SAR) dogs are widely used to locate victims at disaster sites. The efficiency of SAR missions can be greatly enhanced if a canine's emotional states, including their motivation to search, can be remotely estimated in real time. In this study, we developed a real-time emotion estimation system for canines based on measured electrocardiography signals. This proposed system measures a canine's heartbeat intervals using a specially developed canine suit equipped with an electrocardiography device. Using the online heartbeat interval measurements, the system calculates time domain indices of heart rate variability, which are used to classify the canine's emotional state as positive or negative. To support visualization, the system presents the heart rate and estimated emotional state graphically in real time. The real-time emotion estimation system for canines proposed in this study was evaluated using a series of experiments. Bland-Altman analysis showed that online heartbeat interval measurements were consistent with offline heartbeat interval measurements when the canine was at rest or standing still. The proposed system was confirmed operational outdoors in real time and thus has the potential to enhance the efficiency of SAR missions that use canines.

We have developed a method to visualize search and rescue (SAR) dogs' activities from sensor data recorded by the SAR dogs' sensor vests. This paper proposes two methods for detecting continuous barking actions of SAR dogs, which locate victims by smell and then bark continuously to tell handlers where victims are located. Continuous barking action is detected from audio information and a dog's body motions. This detection method is based on dynamic time warping (DTW), which has been used successfully to analyze human audio information. Cyclic body motion was observed during dogs' barking motions. This cyclic motion can be detected by an inertial measurement unit (IMU) attached to the vest. A fast Fourier transform (FFT) is used to analyze a dog's barking motion. The proposed detection methods were evaluated using audio and IMU data recorded during actual SAR dog training sessions. The F-scores of the audio and motion-based barking detection methods were 0.95 and 0.90, respectively. As a trial, we marked victim locations on a map based on the body motion.

Disaster response presents major challenges for robotics and computer vision alike. The Cyber‐Enhanced Canine Suit is a suit equipped with a camera, Global Navigation Satellite System (GNSS), and various other sensors, to be worn by search and rescue (SAR) dogs for the purpose of enhancing SAR dog operations. This paper presents an image recognition system for use in disaster scenarios and its integration with the Cyber‐Enhanced Canine Suit platform. The system’s intended use is to spot personal items of missing individuals or other visual clues in video streams from various disaster response platforms. The system facilitates quick learning of targets from limited data and makes providing that data quick and easy. It also provides backtrack recognition functionality, to rapidly find novel targets in the seen footage. We evaluated the recognition system on footage gathered in the field, obtaining promising results. Integrated with the Cyber‐Enhanced Canine Suit, the system can automatically plot detections of search targets onto a map display, to provide operators with a quick overview of what was seen where.

This chapter introduces cyber-enhanced rescue canines that digitally strengthen the capability of search and rescue (SAR) dogs using robotics technology. A SAR dog wears a cyber-enhanced rescue canine (CRC) suit equipped with sensors (Camera, IMUs, and GNSS). The activities of the SAR dog and its surrounding view and sound are measured by the sensors mounted on the CRC suit. The sensor data are used to visualize the viewing scene of the SAR dog, its trajectory, its behavior (walk, run, bark, among others), and its internal state via cloud services (Amazon Web Services (AWS), Google Maps, and camera server). The trajectory can be plotted on an aerial photograph captured by flying robots or disaster response robots. The visualization results can be confirmed in real time via the cloud servers on the tablet terminal located in the command headquarters and with the handler. We developed various types of CRC suits that can measure the activities of large- and medium-size SAR dogs through non-invasive sensors on the CRC suits, and we visualized the activities from the sensor data. In addition, a practical CRC suit was developed with a company and evaluated using actual SAR dogs certified by the Japan Rescue Dog Association (JRDA). Through the ImPACT Tough Robotics Challenge, tough sensing technologies for CRC suits are developed to visualize the activities of SAR dogs. The primary contributions of our research include the following six topics. (1) Lightweight CRC suits were developed and evaluated. (2) Objects left by victims were automatically found using images from a camera mounted on the CRC suits. A deep neural network was used to find suitable features for searching for objects left by victims. (3) The emotions (positive as well as negative) of SAR dogs were estimated from their heart rate variation, which was measured by CRC inner suits. (4) The behaviors of SAR dogs were estimated from an IMU sensor mounted on the CRC suit. (5) The visual SLAM and inertial navigation systems for SAR dogs were developed to estimate trajectory in non-GNSS environments. These emotions, movements, and trajectories are used to visualize the search activities of the SAR dogs. (6) The dog was trained to search an area by controlling the dog with the laser light sources mounted on the CRC suit.

Abstract. In search and rescue (SAR), time is critical, and successfully finding a lost person in the least amount of time is the goal. Part of a successful search is the development of accurate and relevant search areas. Planning these search areas for lost people can be improved by developing and using spatial models. Spatial models allow for the prediction of a lost person’s movement through the interaction between human navigation behaviour and the underlying terrain. However, they are not often used in real-time SAR. This research looks at spatial models in SAR and outlines the development of an Agent-based model for more accurate search planning and rapid decision-making. The output of the model is discussed, and strategies to engage SAR in the uptake of spatial modelling results are outlined. By incorporating spatial modelling results, it is hoped that search areas can be designed more effectively, which will, in turn, improve the outcomes for lost people.

We propose an underlying system that can infer and visualize search and rescue (SAR) dogs’ behavior. The system is aimed at identifying “run”, “walk”, “stop”, “sniff” and “bark” behaviors of SAR dogs robustly from inertial sensors data, and visualizing the results for the users. In the system, we apply Short-Time Fourier Transform (STFT) to the sensors data, and use a random forest algorithm for learning investigation activities of SAR dogs. We performed an experiment on our system and got the results that some behaviors can be identified precisely. We also developed an on-line visualization system for streaming data of behavior probabilities.

Dogs used for search and rescue (SAR) may experience continuous micro-traumas that predispose them to skeletal disorders. The aim of the present study was to evaluate the effect of diet on osteo-articular apparatus in healthy SAR dogs. A total of sixteen SAR dogs were divided into two groups (low supplementation (LS) and high supplementation (HS)) and were fed for 3 months with two experimental diets, characterised by the same protein and energy density, but different in n-3 PUFA (6·2 v. 8·4 % of metabolisable energy), chondroitin sulfate (219·8 v. 989·0 mg/kg DM) and glucosamine (769·2 v. 1318·7 mg/kg DM) in the LS and HS groups, respectively. At recruitment all dogs showed no joint inflammation signs, except four that showed mild symptoms. Haematology and serum biochemistry were performed every 30 d. Joint status was scored by physical and lameness evaluations. The sampling effect analysis showed potential beneficial effects by a decrease in a specific marker of membrane integrity (creatine kinase; CK). Comparing groups, glucose was significantly higher and CK was significantly lower in the HS group; however, in both cases the levels of these parameters fell in the normal range. At the end of the experiment, erythrocytes, Hb and packed cell volume were significantly higher in the HS compared with the LS group. These could result in an improvement in dogs' performance, even if this aspect was not investigated in the present study. Concerning joint evaluation (pain on manipulation, lameness and range of motion), no statistically significant differences were detected between the groups and within the experimental period.

Social media nowadays are linked almost with every aspect of our lives. They can and have been used to explain social relations, human behaviors, political affections, product preference, just to mention a few applications of social network analysis. Moreover, there are cases in which social media surveillance can be proved valuable for saving human lives as the case which is studied in this book chapter. More specifically, we attempt to test how information collected from social media can improve the ability of a Search and Rescue (SAR) crew to detect people in need using visual search. For the purposes of the study, we simulated a SAR mission in a 3D virtual environment and we asked the study participants to locate refuges needing assistance in different areas of an island. The initial information provided to the volunteers was differentiated and the experiments showed that volunteers who were searching for clues based on input from local social media posts were able to track all the people in need and thus social media surveil-lance was proved to be very promising if it is applied in such cases.KeywordsSocial mediaSurveillanceVisual searchSearch & rescueSocial network analysis

This paper demonstrates the search and rescue (SAR) optimization algorithm for enhancing the performance of the radial distribution system (RDS). Efficient performance can be obtained by optimal network reconfiguration, optimal deployment of distributed generation (DG) and distribution static compensator (DSTATCOM) units into the RDS. These are the effective methods to reduce the power loss in the system. Reduction in real power loss is considered as the fitness function in this paper. This study addresses the various power loss diminution approaches in the network. SAR is a metaheuristic algorithm developed based on human behaviour during search and rescue operations. To demonstrate the potency of the recent SAR algorithm, IEEE 33-bus RDS is utilized for study purposes. The obtained simulation results are compared with the results of other optimization methods. The results obtained are encouraging, with reduced power loss and improved voltage profile in the system.KeywordsDistributed generationDSTATCOMRadial distribution systemSearch and rescue optimizationElectrical power losses