We propose a target detection algorithm that combines confidence and feature extraction to address the problems of existing target detection algorithms, such as low detection accuracy and susceptibility to occlusion. Based on the traditional algorithm, this algorithm introduces the adaptive strategy objective according to the motion complexity of the video block, combined with the target contour field retrieval to enhance the precision of the algorithm. Experimental results show that in different environments, the algorithm in this paper has better detection accuracy and anti-obscuration ability than other existing algorithms. And it still maintains a high resolution for multi-targets, which effectively reduces the problems of target loss, identity jumping, and so on.
KEYWORDS: Education and training, Data modeling, Principal component analysis, Tunable filters, Receivers, Matrices, Linear filtering, Transmitters, Signal attenuation, Interference (communication)
The demand for fall detection technology in elderly individuals is increasing due to the growing global aging population. Wi-Fi's Channel State Information (CSI) based fall detection is gaining popularity as it does not require the installation of expensive cameras or sensors, is not affected by lighting and obstructions, and protects individual privacy. However, previous studies using commercial Wi-Fi and mobile hosts to acquire CSI and recognize falls are expensive. To address this issue, this paper proposes a low-cost fall detection solution based on ESP32-S3 and LSTM model. The proposed solution collects data from 52 subcarriers in the L-LTF, applies Butterworth low-pass filter, and PCA to reduce data dimensionality. The LSTM model achieves a testing accuracy of 96.03%, with 89% classification accuracy for falls. This solution can significantly reduce the cost of fall detection technology and has potential deployment on ESP32-S3. Future research could focus on improving accuracy or exploring different application scenarios.
Based on the exploration or rescue needs of complex areas such as mines and caves, in view of the problems of narrow information detection range, short detection distance, single function, and no obstacle-crossing ability of existing detection robots, an exploration and rescue robot based on ROS system is designed. The surrounding environment information is obtained by 2D lidar, the attitude and acceleration information of the robot is obtained by the attitude sensor (IMU), the autonomous positioning and mapping of the robot is realized by the Gmapping algorithm, and the motor speed is calculated by the path planning algorithm to control the movement of the robot. The test results show that the robot has good motion performance, small size, light weight, strong obstacle-surmounting ability, and strong scalability. It provides first-hand information for the decision-making of the ground command center, and has certain value in the exploration of danger.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.