Indoor Environmental Performance Research Articles

Exploring Asymmetric Lens–Total Internal Reflection (AL–TIR) Optics for Uniform Ceiling Illumination in Interior Lighting

This study presents a significant advancement in LED interior lighting through the development and application of Asymmetric Lens–Total Internal Reflection (AL–TIR) optics, with a focus on enhancing lighting uniformity and indoor comfort by simulating sky-like lighting distribution. AL–TIR technology employs asymmetric lenses combined with total internal reflection to efficiently redirect and spread light, achieving a controlled and even ceiling illumination suitable for various interior applications. This research explored the establishment of ideal luminous intensity curves, devised practical AL–TIR optical designs through numerical calculations, and conducted extensive simulations to assess performance in typical indoor environments. Our findings demonstrated substantial improvements in lighting uniformity, with the AL and AL–TIR systems achieving direct illuminance uniformities of 0.78 and 0.83, respectively, compared to traditional tube LEDs at 0.25. These results, validated in several office rooms, highlight the efficacy of AL–TIR optics in revolutionizing indoor lighting design by balancing optimal lighting distribution with occupant comfort and well-being.

Evaluation of a Kirigami-inspired double-skin adaptive façade for natural ventilation and solar harvesting to enhance indoor environment and energy performance

A novel kirigami-inspired design concept for an environmentally responsive adaptive façade is presented and evaluated for the objectives of solar energy harvesting and adaptive ventilation through controllable surface orientation and opening. The concept is a double-skin façade where the outer skin includes a straight cut kirigami-inspired adaptive component. Controllable actuation of the kirigami-inspired section opens the outer skin for ventilation while also changing the orientation of the outer surface for solar tracking. The primary objective of this study is to evaluate the potential benefits for this concept integrated within a building façade for solar energy harvesting, air changes, and indoor temperature control. As such, a computational study is used to estimate the proposed facade concept's performance within various generalized building-environment scenarios. The methodology is detailed to computationally estimate the potential environmental performance of this concept with respect to solar harvesting with adhered solar panels, as well as air changes and HVAC cost for associated interior spaces. The example scenarios include various building components, from a single room to multiple building stories, and two geographic locations with significantly different environmental conditions, and both daily and yearly performance estimates are shown. The component is most effective when the outdoor temperature is near to the desired indoor temperature and wind speeds are mild, but can still reduce HVAC usage for more disparate temperatures. For example, in the scenarios shown the component can eliminate HVAC use for a 5°C difference between outdoor and indoor temperature and reduces HVAC usage for temperature differences up to 15°C. Moreover, the component has the potential to significantly increase net energy generation, with yearly performance estimated for the scenarios to be as much as 25% greater than that of a flat closed façade. However, the component cut parameters can have a significant impact on environmental performance, and thus require careful design consideration.

Relationship between indoor environmental quality and guests’ comfort and satisfaction at green hotels: A comprehensive review

Abstract Recent studies have focused on different aspects of green management, practices, and green consumption in the hotel industry. However, there is a need to explore and better understand the association between indoor environmental quality (IEQ) and green hotel guest’s comfort. Therefore, it is essential to explore the effects of IEQ on the comfort and satisfaction of green hotel guests. This study conducts a comprehensive review of the effects of various IEQ parameters, including indoor air quality, thermal comfort, lighting, visual/view, acoustic comfort, building characteristics, decoration, and indoor greenery, on guest’s comfort and satisfaction in green hotels. Based on previous literature, it was also revealed that most current green building schemes lack of comprehensive evaluation of the performance of IEQ dimensions in green hotels. It was also observed that these IEQ parameters show a significant influence on the hotel guest’s comfort and satisfaction. Based on the findings of the literature review, a conceptual model was developed to represent the relationship between the IEQ parameters and guest’s comfort and satisfaction. The proposed conceptual model can be implemented by the hotel management for a comprehensive assessment of guests’ perceptions toward the IEQ in green hotels. The novelty of this study is based on its findings that establish a more effective IEQ evaluation method and serve as the reference scenario of IEQ, which can be a useful tool for both academician and practitioners and contribute to improving the indoor environmental performance of green hotels through highlighting the key IEQ parameters, which affect the comfort and satisfaction of hotel guests.

Enhancing Bluetooth Channel Sounding Performance in Complex Indoor Environments

Enhancing Bluetooth Channel Sounding Performance in Complex Indoor Environments

Hardware Development and Evaluation of Multihop Cluster-Based Agricultural IoT Based on Bluetooth Low-Energy and LoRa Communication Technologies.

In this paper, we present the development and evaluation of a contextually relevant, cost-effective, multihop cluster-based agricultural Internet of Things (MCA-IoT) network. This network utilizes commercial off-the-shelf (COTS) Bluetooth Low-Energy (BLE) and LoRa communication technologies, along with the Raspberry Pi 3 Model B+ (RPi 3 B+), to address the challenges of climate change-induced global food insecurity in smart farming applications. Employing the lean engineering design approach, we initially implemented a centralized cluster-based agricultural IoT (CA-IoT) hardware testbed incorporating BLE, RPi 3 B+, STEMMA soil moisture sensors, UM25 m, and LoPy low-power Wi-Fi modules. This system was subsequently adapted and refined to assess the performance of the MCA-IoT network. This study offers a comprehensive reference on the novel, location-independent MCA-IoT technology, including detailed design and deployment insights for the agricultural IoT (Agri-IoT) community. The proposed solution demonstrated favorable performance in indoor and outdoor environments, particularly in water-stressed regions of Northern Ghana. Performance evaluations revealed that the MCA-IoT technology is easy to deploy and manage by users with limited expertise, is location-independent, robust, energy-efficient for battery operation, and scalable in terms of task and size, thereby providing a versatile range of measurements for future applications. Our results further demonstrated that the most effective approach to utilizing existing IoT-based communication technologies within a typical farming context in sub-Saharan Africa is to integrate them.

Research on Application of Composite Facades for Civilian Reconstruction of Industrial Heritage in Cold Regions Based on Thermal Buffering Effect

Previous studies on the civil transformation of industrial heritage have been conducted mainly from the perspective of architectural history, culture and aesthetics, but rarely focus on energy-saving and the comfort of the new users. Most industrial heritage facades are of high conservation value, but efforts to preserve the authenticity of the facade can lead to the application of limited energy-saving technologies, ultimately resulting in poor indoor thermal environments. Therefore, it is valuable to research how to solve the contradiction between protecting the authenticity of the preserved facades of industrial heritage and improving the indoor environmental performance. This paper proposes two composite facade application strategies based on thermal buffer effects, takes two composite facades renovation methods of Shenyang Dongmao No. 2 Warehouse as an example, utilizes the natural environmental resources to enhance the spatial quality of industrial heritage. With the help of DesignBuilder software modelling simulation analysis, in-depth comparative analysis of the two types of composite facades on the indoor thermal environment of the industrial heritage of the impact and scope. Key findings show that the application of two different composite facade retrofitting techniques not only protects the skin texture of the wall, but also effectively increases the indoor temperature and reduces the indoor energy consumption of the industrial heritage. The composite facade of the external solid wall and the internal glass is more stable in raising the indoor temperature, more effective in reducing the building energy consumption, and more suitable for the civilian transformation of industrial heritage in cold areas. The research findings provide reference for studies on the civil transformation of industrial heritage, and serve as technical references for architects.

Correlating working performance with thermal comfort, emotion, and fatigue evaluations through on-site study in office buildings

The primary objective of creating an indoor thermal environment is to ensure thermal comfort and to enhance the working performance of occupants, particularly in office buildings. This study investigates the factors influencing working performance and their interrelationships. Based on this, the influence mechanism and prediction model of working performance were investigated. An on-site study was conducted to assess indoor environment, thermal comfort, emotion, fatigue and working performance in office settings across different seasons. The findings indicate that the indoor environment and thermal comfort vary with the seasons. The working performance is affected by environment, thermal comfort, emotion and fatigue. Different facets of working performance relate to distinct cognitive abilities and exhibit various patterns of change. In terms of thermal sensations, cognition, perception, and attention generally improved under neutral or slightly warm conditions, whereas cold conditions seemed to enhance thinking. Furthermore, a model integrating thermal comfort, emotion, and fatigue with working performance was developed, offering deeper insights into the mechanisms influencing working performance. A predictive model for working performance was also established, incorporating thermal comfort, fatigue, and emotion as variables. The model achieved an R2 value of 0.749, with a MAE of 0.079 and a RMSE of 0.105. In the Total Sensitivity Index for working performance, values corresponding to thermal comfort, emotion, and fatigue are 0.648, 0.339, and 0.511, respectively. This implies that thermal comfort is the most critical factor influencing working performance. The insights derived from these studies can serve as valuable references for designing indoor thermal environments.

3D reconstruction of semantic-rich digital twins for ACMV monitoring and anomaly detection via scan-to-BIM and time-series data integration

Current research in air-conditioning and mechanical ventilation (ACMV) operation focuses on isolated sub-processes and analytical models. Digital twins, as digital replicas of assets, processes, or systems in the built environment, enable facilities manager (FM) to gain insights into the physical features of space, equipment performance, and energy efficiency. This study presents the 3D reconstruction of semantic-rich digital twins, which encompasses conditional and machine learning-enabled monitoring with 3D geometric models, for ACMV modeling and operation. The proposed framework involves a hybrid rule-based and data-driven approach to forecast the performance of indoor environment and identify potential anomalies throughout ACMV operation. Following this, a scan-to-BIM process is undertaken, with the aid of Simultaneous Localization and Mapping algorithms, to semi-automatically generate the as-built geometric models. Lastly, semantic enrichment of BIM is performed by incorporating time-series data from the rule-based and data-driven approach with 3D geometric models. The proposed approach supports the reconstruction of content-aware and semantic-rich digital twins, which utilize sensor-derived time-series data and 3D geometric models, to conduct advanced analysis for intelligent ACMV operation towards energy efficiency and occupant comfort.

Passive continuous-variable quantum key distribution based on orthogonal frequency-division multiplexing in the terahertz band

We propose a passive continuous-variable quantum key distribution protocol based on multicarrier multiplexing technology in the terahertz band. In this paper, we realize the superposition of multipath coherent states by inverse Fourier transform and passive modulation. At the receiving end, the coherent states of the subcarriers are separated by quantum Fourier transform, and the keys are obtained in parallel by a homodyne (heterodyne) detector and post-processing. In addition, we derive the security bounds of the protocol and evaluate the performance in indoor environments and intersatellite links. Furthermore, we consider finite-size effects and propose tighter agreement constraints, which are more practical than those obtained in the asymptotic limit. This work will provide an effective way to build efficient wireless quantum communication networks.

Reinforcement learning control of multi-spectral LED systems for rendering optimal lighting performance in indoor environment

Light-emitting diodes (LEDs) have superseded traditional light sources due to their superior qualities. However, achieving desired spectral distribution in indoor environment still remains a challenge, particularly for optimizing multiple lighting parameters, which are nonlinear functions of the light spectra, including correlated color temperature (CCT), color rendering index (CRI) and circadian action factor (CAF). Existing studies have been mainly devoted to seeking optimal solutions, by means of various optimization methods, e.g. genetic algorithms. However, these methods can only result in fixed recipes to achieve pre-assigned reference parameters, and cannot meet the need of dynamic varying lighting environment. Therefore, this paper proposes a novel framework for optimal spectrum design and control in multichannel LED lighting systems. It surpasses traditional methods by employing reinforcement learning (RL) to generate an entire optimal spectral power distribution (SPD) model, comprehensively considering CCT, CRI, CAF, and other relevant parameters. This framework integrates the RL-based optimal SPD generator with a corresponding real-time controller, bridging the gap between simulations and real-world applications. The effectiveness of this new framework has been verified by an experimental prototype, showcasing both the optimal SPD and the achieved control performance. This work paves the way for high-quality, user-centric lighting with dynamic CCT and spectral control, and enables the creation of lighting environments that optimize human well-being, productivity, and overall experience.

EXPLORING THE POTENTIAL OF VEGETATION STRUCTURES (VS) AND LANDSCAPE ORIENTATION IN MINIMIZING THERMAL PERFORMANCE IN A TROPICAL CLIMATE: A FIELDWORK STUDY

The study investigates the impact of vegetation structure within two landscape orientations on thermal performance, a critical consideration in urban planning and environmental management. Given the increasing concerns about Urban Heat Islands and global warming, understanding how vegetation influences thermal regulation is essential. This research employed a quantitative method through field measurement studies, focusing on two single-storey semi-detached houses namely East Landscape Orientation (ELO) and West Landscape Orientation (WLO) located at Seri Iskandar, Perak Malaysia. The snowball technique was utilized to select the case study houses, ensuring a targeted approach to understanding the effects. Thermal Microclimate Data Logger and Indoor Air Quality Monitor Data Logger were used to measure environmental parameters for thermal conditions, ensuring consistent, reliable, and comprehensive data for analyzing thermal performance in both outdoor and indoor environments. The research findings reveal that the orientation of a house relative to the sun's path significantly impacts its thermal dynamics, with vegetation playing a crucial role in moderating these effects. ELO houses benefit from milder morning sunlight and effective afternoon cooling, while WLO houses experience higher outdoor and indoor temperatures due to intense sunlight and less efficient transpiration by vegetation. Vegetation on the west side provides shade and reduces heat absorption, improving comfort and energy efficiency. Understanding these dynamics can help homeowners and architects make informed decisions about landscape design, enhancing thermal comfort and energy efficiency in homes. This research also contributes to the expanding knowledge base on sustainable urban design by exploring the use of vegetation to enhance thermal performance.

Analytical model and comprehensive index construction of indoor air purification effect based on dynamic characteristics and energy efficiency

Meeting environmental regulation requirements while improving energy usage efficiency are crucial endeavors to achieve decarbonization and indoor environmental regulation. In this study, experimental testing, data analysis, and modeling are performed for the dynamic purification process of indoor PM2.5 (fine particulate matter) in the context of regulating the indoor environment of buildings. The results show that indoor PM2.5 levels are dynamically matched to the outdoor environment state and the requirements of environmental control. An analytical model of the effect of PM2.5 purification is constructed, which can accurately reflect the dynamic changes in the PM2.5 mass concentration during the indoor air purification process considering the outdoor PM2.5 concentration and the purification efficiency of the purification filters and purification systems, thus supporting the prediction of purification outcomes and accurately constraining the actual indoor air quality purification process. Meanwhile, an indoor air quality control index (IAQCI) is established based on the purification effect and purification energy efficiency under various combinations of air filters and purification systems. This approach is used to quantitatively assess the dual control of energy efficiency and environmental regulation, as well as the purification effect and efficiency of indoor purification schemes based on outdoor dynamic PM2.5 conditions.This study provides a set of innovative and feasible research methods for realizing comprehensive indoor environmental performance evaluations of buildings.

Indoor environmental quality in schools: NOTECH solution vs. standard solution.

In many Danish schools, the indoor environmental quality (IEQ) is challenged and studies document a poor IEQ in a majority of existing schools. Municipalities cannot afford comprehensive renovations and expensive mechanical ventilation solutions, hence public schools often suffer from poor indoor environment conditions. This study tests a new façade based, demand-controlled ventilation solution called NOTECH in the renovation of school. The study tests NOTECH vs. existing mechanical ventilation solution, comparing performance of both solutions at Skovbrynet Skole in Denmark. The project investigates the effect of the NOTECH solution in a primary school classroom, comparing it to a similar classroom with conventional, mechanical ventilation. Methodically, indoor environmental quality and energy performance is monitored in the two identical classrooms during one school year 2018 - 2019. The results show that both systems keep the conditions within acceptable limits and CO2 levels below 1000 ppm, which is the requirement according to the Danish Building Regulations. In terms of costs, the NOTECH system has a lower overall cost than the mechanical ventilation system, with total estimated costs for installation, heating, electricity and maintenance amounting to approximately 35% of the mechanical system's costs. Finally, the results show that the NOTECH solution has a smaller embedded CO2 footprint for building materials, reducing the estimated carbon load by 95% compared to the mechanical ventilation solution. While the performance of the both systems complies to the Danish Building Regulations, the indoor environmental quality between systems differs significantly. Results showing a higher air-temperature and lower relative air-humidity in the classroom with mechanical ventilation during winter and lower CO 2 levels in the mechanically ventilated classroom during winter and summer. Costs for implementation, energy consumption for heating and CO 2 footprint for building materials are significantly lower for the NOTECH solution, compared to the mechanical solution.

Implementation of Intelligent Indoor Service Robot Based on ROS and Deep Learning

When faced with challenges such as adapting to dynamic environments and handling ambiguous identification, indoor service robots encounter manifold difficulties. This paper aims to address this issue by proposing the design of a service robot equipped with precise small-object recognition, autonomous path planning, and obstacle-avoidance capabilities. We conducted in-depth research on the suitability of three SLAM algorithms (GMapping, Hector-SLAM, and Cartographer) in indoor environments and explored their performance disparities. Upon this foundation, we have elected to utilize the STM32F407VET6 and Nvidia Jetson Nano B01 as our processing controllers. For the program design on the STM32 side, we are employing the FreeRTOS operating system, while for the Jetson Nano side, we are employing ROS (Robot Operating System) for program design. The robot employs a differential drive chassis, enabling successful autonomous path planning and obstacle-avoidance maneuvers. Within indoor environments, we utilized the YOLOv3 algorithm for target detection, achieving precise target identification. Through a series of simulations and real-world experiments, we validated the performance and feasibility of the robot, including mapping, navigation, and target detection functionalities. Experimental results demonstrate the robot’s outstanding performance and accuracy in indoor environments, offering users efficient service and presenting new avenues and methodologies for the development of indoor service robots.

Benefits of thermal and distance-filtered imaging for wayfinding with prosthetic vision

Visual prostheses such as the Argus II provide partial vision for individuals with limited or no light perception. However, their effectiveness in daily life situations is limited by scene complexity and variability. We investigated whether additional image processing techniques could improve mobility performance in everyday indoor environments. A mobile system connected to the Argus II provided thermal or distance-filtered video stimulation. Four participants used the thermal camera to locate a person and the distance filter to navigate a hallway with obstacles. The thermal camera allowed for finding a target person in 99% of trials, while unfiltered video led to confusion with other objects and a success rate of only 55% (p<0.01\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$p<0.01$$\\end{document}). Similarly, the distance filter enabled participants to detect and avoid 88% of obstacles by removing background clutter, whereas unfiltered video resulted in a detection rate of only 10% (p<0.01\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$p<0.01$$\\end{document}). For any given elapsed time, the success rate with filtered video was higher than with unfiltered video. After 90 s, participants’ success rate reached above 50% with filtered video and 24% and 3% with normal camera in the first and second tasks, respectively. Despite individual variations, all participants showed significant improvement when using the thermal and distance filters compared to unfiltered video. Adding a thermal and distance filter to a visual prosthesis system can enhance the performance of mobility activities by removing clutter in the background, showing people and warm objects with the thermal camera, or nearby obstacles with the distance filter.

Efficiency Analysis of the Photovoltaic Shading and Vertical Farming System by Employing the Artificial Neural Network (ANN) Method

Productive facades, consisting of photovoltaic shading and vertical farming systems, have been proposed as a means to improve the thermal and visual status of residential buildings while also maintaining energy performance and providing vegetables. However, how to quickly and accurately predict electricity and vegetable output during the numerous influencing architectural and environmental factors is one of the key issues in the early stages of design, and few studies have investigated the impact of such structures on both indoor environmental qualities and production performance. In this paper, we present a novel prediction method that uses experimental data to train and test an artificial neural network (ANN). The results indicated that using the Bipolar Sigmoid activation function to process the experimental data input to the artificial neuron network gives more accurate predicted results both in the yield of photovoltaic shading and vertical farming systems. In addition, this prediction method was applied to a typical high-rise residential building in Singapore to assess the self-sufficiency potential of high-rise residential buildings integrated with productive facades. The results indicated that the upper part of the building can meet 20.0–23.1% of the annual household electricity demand of a family of four in a four-room residential unit in Singapore and almost the entire year’s vegetable demand, while the middle part can meet 18.4–21.2% and 89.1%, respectively. The results demonstrated the importance of a productive facade in reducing energy demand, enhancing food security, and improving indoor visual and thermal comfort.

Indoor environmental quality in schools: NOTECH solution vs. standard solution

Background: In many Danish schools, the indoor environmental quality (IEQ) is challenging and studies document a poor IEQ in a majority of existing schools. Municipalities cannot afford comprehensive renovations and expensive mechanical ventilation solutions, hence public schools often suffer from poor indoor environment conditions. This study tests a new façade based, demand-controlled ventilation solution called NOTECH in the renovation of school. The study tests NOTECH vs. existing mechanical ventilation solution, comparing performance of both solutions at Skovbrynet Skole in Denmark. Methods: The project implements and investigates the effect of the NOTECH solution in a primary school classroom, comparing it to a similar classroom with conventional, mechanical ventilation. Methodically, indoor environmental quality and energy performance is monitored in the two identical classrooms during one school year 2018 - 2019. Results: The results show that both systems keep the conditions within acceptable limits and CO2 levels below 1000 ppm, which is the requirement according to the Danish Building Regulations. In terms of costs, the NOTECH system has a lower overall cost than the mechanical ventilation system, with total estimated costs for installation, heating, electricity and maintenance amounting to approximately 35% of the mechanical system’s costs. Finally, the results show that the NOTECH solution has a smaller embedded CO2 footprint for building materials, reducing the estimated carbon load by 95% compared to the mechanical ventilation solution. Conclusions: The performance of the two systems roughly is the same in relation to the indoor environmental quality, temperature, CO2 levels and relative air-humidity. Costs for implementation, energy consumption for heating and CO2 footprint for building materials however, are significantly lower for the NOTECH solution, compared to the mechanical solution.

Adaptive thermal comfort in the offices of three climates of North-East India

Buildings not only provide shelter to the occupants but also security, safety and comfort, as well as signifying economic and socio-cultural status. The high energy intensity of buildings has become a matter of concern worldwide in the context of climate change and global warming. Adaptive comfort principles and guidelines afford greater design opportunities for reduced energy intensity without compromising occupant thermal comfort and indoor environmental quality performance. However, thermal adaptation opportunities of office occupants in the North-Eastern part of India are rarely addressed by previous thermal comfort studies conducted in the Indian subcontinent. A yearlong questionnaire-based adaptive thermal comfort study with concurrent indoor environmental measurements was conducted in naturally ventilated office buildings located in three locations, i.e., Tezpur, Imphal and Shillong, representing the climatic zones of North-East India. A total of 2326 valid questionnaire responses were collected. ASHRAE Class-II field study protocols, seven-point thermal sensation and five-point preference scales were used to collect objective and subjective comfort assessments. It was found that the clothing insulation (clo) levels worn by occupants varied non-linearly with indoor temperatures. The estimated preferred temperatures for building occupants in Tezpur, Imphal and Shillong were 24 °C, 23.5 °C and 22 °C, respectively. Probit analysis of thermal sensation data indicated that the indoor temperature stimulus associated with a shift of one thermal sensation unit differed between the warm and cool side of the 7-point thermal sensation scale. Increasing indoor air velocity up to 0.8m/s shifted the upper threshold of discomfort to 32 °C. It was also found that 80% of office occupants were comfortable within the temperature range of 25 °C–30 °C. The adaptive comfort model derived from the current database shows lower sensitivity of subjects to outdoor temperature changes compared to existing International standards like ASHRAE Standard 55 or EN16798. The present study demonstrates the potential for low-energy, naturally ventilated office design strategies in similar climatic conditions in North-East India and other parts of the world. Above all, it enriches the worldwide thermal comfort database.

Marker-Based Localization System Using an Active PTZ Camera and CNN-Based Ellipse Detection

Localization in GPS-denied environments is challenging, and many existing solutions have infrastructural and on-site calibration requirements. This article tackles these challenges by proposing a localization system that is infrastructure free and does not require on-site calibration, using a single active pan–tilt–zoom camera to detect, track, and localize a circular LED marker. We propose to use a convolutional neural network (CNN) trained using only synthetic images to detect the LED marker as an ellipse and show that our approach is more robust than using traditional ellipse detection without requiring tuning of parameters for feature extraction. We also propose to leverage the predicted elliptical angle as a measure of uncertainty of the CNN's predictions and show how it can be used in a filter to improve marker range estimation and 3-D localization. We evaluate our system's performance through localization of a unmanned aerial vehicle in real-world flight experiments and show that it can outperform alternative methods for localization in GPS-denied environments. We also demonstrate our system's performance in indoor and outdoor environments.

A deep-learning framework running on edge devices for handgun and knife detection from indoor video-surveillance cameras

The early detection of handguns and knives from surveillance videos is crucial to enhance people’s safety. Despite the increasing development of Deep Learning (DL) methods for general object detection, weapon detection from surveillance videos still presents open challenges. Among these, the most significant are: (i) the very small size of the weapons with respect to the camera field of view and (ii) the need of a real-time feedback, even when using low-cost edge devices for computation. Complex and recently-developed DL architectures could mitigate the former challenge but do not satisfy the latter one. To tackle such limitation, the proposed work addresses the weapon-detection task from an edge perspective. A double-step DL approach was developed and evaluated against other state-of-the-art methods on a custom indoor surveillance dataset. The approach is based on a first Convolutional Neural Network (CNN) for people detection which guides a second CNN to identify handguns and knives. To evaluate the performance in a real-world indoor environment, the approach was deployed on a NVIDIA Jetson Nano edge device which was connected to an IP camera. The system achieved near real-time performance without relying on expensive hardware. The results in terms of both COCO Average Precision (AP = 79.30) and Frames per Second (FPS = 5.10) on the low-power NVIDIA Jetson Nano pointed out the goodness of the proposed approach compared with the others, encouraging the spread of automated video surveillance systems affordable to everyone.