BYBo Yang

Bo Yang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Bo Yang has a total of 28 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Human Activity Recognition by Fusing Ultrawideband Radar and Low-Resolution Infrared Information

    by Linzi Min, Bo Yang, Guoqing Dai, Mengru Wang

    The recognition of continuous daily human action is of great significance in smart homes, health management, and other areas. It is the key to achieving “Big Health” model. Both thermopile infrared array sensor (TPAS) and impulse radio ultra-wide band (IR-UWB) radar can detect human target and provide relative rich information without privacy invasion. This paper builds a hardware platform based on these two types of sensors, collects data from actual indoor scenes, and proposes a human action recognition algorithm for achieving human action segmentation, human target localization and recognition of multi-level activities. A human action segmentation algorithm is proposed based on finite state machine (FSM) and R-square value. Three data fusion schemes are designed based on CNN network: data level fusion, feature level fusion, and decision level fusion to recognize human actions. A positioning algorithm is proposed fusing TPAS and UWB information to determine orientation and distance. Finally, a scene model is established containing location, objects, spatial and temporal information, and Hidden Markov Model (HMM) is trained to encode the information and predict high semantic human activities. The experimental results show that the accuracy for human dynamic recognition reaches 97.22%, the success rate of human positioning achieves 92.03% and the system can accurately recognize continuous human actions and high semantic activities in actual scenes.


  • Multimodal sensor image enhancement for runway detection under low visibility

    by Haoxiang Shi, Bo Yang, Zhaozi Zu, Zhongjun Qu

    Aircraft landing, especially under conditions of low visibility, often requires specialized equipment for assistance. However, due to high construction and maintenance costs associated with traditional ground-based landing assistance, there is a growing interest in using onboard sensors for navigation as an alternative. This paper addresses the scenario of aircraft landing under low visibility conditions with onboard visible and infrared sensors, enhancing visible images with infrared images for improving visibility, then use enhanced images for runway detection to guide visual navigation. There are mainly two significant challenges: multimodal sensor image registration and detailed runway detection. Due to the different installation positions of sensors, the images captured by different sensors need pixel-level alignment, but multimodal sensor images often contain many distinct features which makes it challenging to find their accurate correspondences. Additionally, simply identifying the runway area is not enough, detailed detection of runway lines is also necessary. To address these issues, this paper proposes a framework which begins with a registration network embedded a plug-and-play modality transfer module to improve multimodal registration performance. A fusion method is then used to enhance ready-aligned images, followed by a two-stage detection strategy to detect lines of runway at various landing distance. Experimental results show that the enhanced images from different sensors with detailed detection can effectively improve detection accuracy.


  • Non-Contact Respiratory and Heart Rate Detection Using IR-UWB Radars Under Random Body Activity

    by Bo Yang, Linzi Min, Mengru Wang, Haoxiang Shi

    In recent years, more and more attention has been paid to the daily detection of vital signs. Using impulse radio ultra-wideband (IR-UWB) radars to detect vital signs (respiratory rate and heart rate) has become a research hotspot. In healthcare, a long-term continual monitoring of vital signs is required. But most research works on vital signs detection assume that the subjects always remain stationary, however the random activity of human body is inevitable for a long period of monitoring. This paper proposes a new simple and effective algorithm for vital signs detection using only one IR-UWB radar under random activity of human body, consisting of region of interest detection, respiratory signal extraction, and motion detection. And the vital signs detection is finally realized when the subjects sit at desks and do daily work accompanied with common random body activities, e.g., shaking body, using phones, turning head. The experimental results show that the motion detection can effectively improve the detection accuracy of respiratory rate and heart rate.


  • Occluded Multi-Human Target Segmentation in Dynamic Indoor Scenes Based on Thermopile Array Sensor

    by Mengni Yang, Bo Yang, Haoxiang Shi

    Low-resolution thermopile infrared array sensor (TPAS), has gained increasing attention for real-time perception and monitoring of indoor human targets. Most recent researches focus on single individual just because of its low resolution of TPAS. Additionally, there are many dynamically changing heat sources besides human targets in indoor environments. The dynamic background removal and occluded human instances distinction encounter significant challenges in low resolution based on thermopile infrared array sensor. To address the interference of dynamic heat sources in multi-person indoors scenarios, this paper proposes an algorithm called adaptive Gaussian background removal algorithm applying a priori map for multi-human (AGBR-PMM). Additionally, to enhance the subsequent human behavior recognition performance, it is necessary to segment occluded human targets after removing indoor heat source interference and extracting all human targets. PANet is employed to segment different human regions, particularly the areas with occluded individuals. A combination of these two methods in low-resolution scenes achieves a good segmentation of occluded human instances while eliminating interferences from dynamic indoor scenes. It outperforms AGBR-PMM and PANet alone in terms of accuracy, precision, and F1-score of 97%, 92%, and 94%, respectively. This lays the foundation for subsequent human behavior recognition using low-resolution thermopile infrared array sensor.


  • Open Access

    OMSLD: Occlusion-Aware Multi-human Segmentation in Low-resolution Infrared Dynamic Scene

    by Mengni Yang, Bo Yang, Haoxiang Shi

    Due to the advantages of preserving privacy, low-resolution thermopile infrared array sensor (TPAS), as an alternative to visible light sensor, has gained increasing attention for real-time perception and monitoring of indoor human targets. However, most recent research focus on single individual just because of its low resolution. Additionally, there are many dynamically changing heat sources besides human targets in indoor environments. The switching states, positional movements of interfering heat sources, as well as occlusions between interfering heat sources and humans and among humans themselves, pose a great challenge and bear significance to the task of removing dynamic background and distinguishing occluded human instances in low resolution. This paper proposes a new infrared occluded multi-human segmentation network based on Mask R-CNN and designs a new multi-scale fusion feature pyramid detection network. A hardware platform is constructed based on a TPAS with 24×32 pixels. The improved Mask R-CNN can effectively segment occluded multi-human instances even in low-resolution dynamically changing scenarios. However, there is still possible to segment dynamic indoor heat sources as human targets. To address this issue, this paper introduces an adaptive Gaussian background removal algorithm applying a priori map for multi-human (AGBR-PMM). A combination of these two methods in low-resolution scenes achieves good segmentation of occluded human instances while eliminating interferences from dynamic indoor scenes. This lays the foundation for subsequent human behavior recognition using low-resolution thermopile infrared array sensor.

  • Application of A Priori Map in Dynamic Background Removal for Indoor Human Perception Using a Thermopile Array

    by Tong Zhang, Bo Yang, Nanhao Gu

    Human perception is of great research and application value. Thermopile infrared array sensor (TPAS) is an available solution without privacy invasion. In specific indoor environment like apartment and office, there are inevitable interfering thermal sources except human. Extracting human from the dynamically changing background i.e. background removal is a critical process. Based on the hardware platform built by a thermopile infrared array sensor MLX90640 with an output of ${24}\times {32}$ pixels, this paper proposes an adaptive Gaussian background removal algorithm applying a priori map (AGBR-PM) for indoor single human perception. For each static thermal source, an a priori map is established containing its location and thermal radiation feature in the way of support degree matrix. We build a Gaussian background model consisting of mean and standard deviation matrix. Each frame of thermal image is segmented into foreground and background based on $2\sigma $ rule. A state and cross detection algorithm is proposed to compensate the error caused by interfering static thermal sources, and an erosion-connected component analysis and foreground complement algorithm is adopted to reduce the random noise as well. A regional update strategy is designed to adapt to the emergence of random thermal sources in background. The experimental results have shown that AGBR-PM has an excellent adaptability to dynamically changing environment, and can remove the background correctly.


  • A dual-typed and omnidirectional infrared perceptual network for indoor human tracking

    by Bo Yang, Fuhuang Liu

    This paper proposes a dual-typed and omnidirectional infrared perceptual network for indoor human target location and tracking. Two types of infrared sensors, pyroelectric infrared sensors and thermopile array sensors, are used in the sensor network for side-view and top-view perception respectively. The sensor nodes are deployed to construct an omnidirectional sensing model for detecting human targets in an indoor scenario with irregular boundary, furniture and other obstacles. The improved credit location algorithm and the adaptive threshold algorithm are applied for the human location. The location ambiguity existing in the actual situations is analysed and the compensation methods are designed by using an equivalent measurement line and a state machine to reduce the location ambiguity. Finally, a fuzzy adaptive CS-jerk (current statistical-jerk) algorithm is applied for tracking the human target. The tracking results indicate that the dual-typed and omnidirectional system works well in the indoor environment.


  • Traffic Flow Detection Using Thermopile Array Sensor

    by Yukexin Zhang, Bo Yang

    The Intelligent Transportation System (ITS) has been developed rapidly in recent years. As a significant part of the ITS, the collection of traffic information relies on the detection of vehicles by using various sensors, in which micro-electro-mechanical system (MEMS) sensors have been widely investigated. A representative of MEMS sensors is magnetoresistance sensor with stable performance. However, it is hard to detect very low-speed congested traffic. The MEMS thermopile array sensor currently used for human detection can detect stationary infrared objects, including the ignited vehicles. It could be an alternative to detect the vehicles under heavily congested traffic condition. This paper proposes a traffic flow detection method using such a thermopile sensor by the roadside. Traffic flow data are collected and analyzed through a procedure of data preprocessing, background removal, morphology operation, and vehicle detection. A visual background extractor (ViBE) is used in background removal and a finite-state machine (FSM) is designed to reduce the detection error. Different experiments test the detection method in the absence and presence of high temperature interference. The experimental results indicate that the proposed method can successfully detect the traffic flow and it is suitable for occasions where the ambient temperature differs obviously from the vehicle temperature.