8 results about "Video sensors" patented technology

Nonintrusive approaches for vital signs detection and tracking represent appealing methods for improving wellness in broad population ranges and detecting / monitoring health conditions among medical patients. Both industry and academia have shown significant interest in providing reliable contactless reading of vital signs using common video sensors and light modulation properties coming from blood circulation in human skin. Existing approaches propose solutions that can extract the heart rate signal from human faces; they also address the noise challenges from the environment with partial success. We aim to provide accurate heart rate readings from human subjects and human face in situations where temporary in-band noise from subject head motion and lightness changes may occur. Our contribution creates multiple reading channels and brings forth a detection—and tracking method that can efficiently cope with the noise, providing reliable heart-rate readings in stressful conditions. In addition, the method we propose does not rely on sophisticated AI blocks and is, thus, applicable for implementation on embedded and mobile devices with limited processing resources. We demonstrate the claim by implementing and running our method on several embedded and mobile platforms.

The application discloses a pedestrian target detection method based on radar video infrared decision-level fusion, and relates to the technical field of automatic driving perception. The application aims to solve the problem that the existing pedestrian detection method uses a single mode of video sensor to perform a pedestrian target detection task under poor light conditions, and the intelligent driving vehicle has more false detection and missed detection conditions for pedestrian detection, so that the intelligent driving vehicle depending on ADAS cannot timely avoid pedestrians and makes an incorrect driving strategy and even a collision occurs. The process is as follows: a pedestrian detection platform is built; laser radar, visible light cameras and infrared cameras are time and space aligned; pedestrian targets in laser radar point clouds, pedestrian targets in visible light images and pedestrian targets in infrared images are detected; target detection results are fused based on a decision-level fusion algorithm to obtain final pedestrian target detection results.

The application relates to the technical field of vehicle-mounted rearview mirrors, in particular to a vehicle-mounted electronic rearview mirror circuit and a vehicle-mounted electronic rearview mirror. The vehicle-mounted electronic rearview mirror circuit comprises a video acquisition module, the video acquisition module comprises video sensors arranged at multiple visual angles of a target vehicle; the output end of the video acquisition module is connected with the input end of a video conversion module, the output end of the video conversion module is connected with the signal input end of a main control module; the first driving end of the main control module is connected with the backlight input end of a driving module, the second driving end of the main control module is connected with the display input end of the driving module; the backlight driving end of the driving module is connected with the first input end of a display module, the display driving end of the driving module is connected with the second input end of the display module, and the display module comprises a plurality of display screens. The application can provide comprehensive surrounding vision for a driver, thereby eliminating the problem of frequent conversion of the driver's vision, reducing the risk of distraction, and improving the convenience and safety performance of driving.

This invention relates to the field of blast furnace ironmaking technology and discloses a blast furnace tuyere combustion temperature monitoring device to solve the problem of discrepancies between existing theoretical combustion temperature calculations and actual values. The device includes a tuyere combustion temperature monitoring probe and an industrial control computer. The probe incorporates a coaxial optical video sensor and a temperature sensor, and uses a beam splitter to divide the reflected light from the target into two paths: one path is used for sensor measurement, and the other path passes through a reflector and enters the eyepiece. The probe's front end is equipped with a quick-connect sleeve to fix it to the tuyere viewing hole. This invention achieves "what you see is what you measure" through eyepiece and beam splitting adjustment, effectively avoiding interference from the spray gun and unburned particles. Combined with dual infrared colorimetric temperature measurement technology, it achieves accurate, real-time online monitoring of the actual combustion temperature at the tuyere, providing reliable data support for refined blast furnace operation and the injection of new materials such as hydrogen-rich gas.

To provide a system and method for determining target characteristics during laser treatment. [Solution] The method includes the step of (i) obtaining a relationship between (i) the number of pixels related to a light beam reflected from a target or an object located in close proximity to the target on an endoscopic image acquired from a video sensor coupled to the endoscope, and (ii) the distance from the tip of the endoscope to the target. The method further includes the step of (ii) measuring the number of pixels related to the light beam reflected from the target or the object located in close proximity to the target during the procedure, and (iii) determining at least one of the size of the target or the distance from the tip of the endoscope to the target, at least in part based on the relationship acquired in step (i) and the number of pixels measured in step (ii).

The utility model discloses a kind of desert steppe precision grazing control devices in the technical field of grazing control equipment, the device includes central processing unit and multiple monitoring components and sound driving component connected with central processing unit, monitoring component includes the video sensor for collecting livestock image information and the spectrum sensor for collecting pasture spectrum information, sound driving component includes sound and sound sensor and sound insulation mechanism.The utility model plays the sound for driving away livestock by central processing unit opening sound when livestock enters low vegetation coverage area, avoid livestock overeating pasture, shield sound regularly by sound sensor and sound insulation mechanism, avoid livestock long-term stress, after livestock is transferred to other grassland area, the pasture of previously eaten area can recuperate, sustainable development grassland ecological environment, so that ranch manager can reasonably and orderly carry out grazing activity.

An intelligent, standalone, and modular secure parcel management platform integrates Internet of Things (IoT) architecture with artificial intelligence (AI) and machine learning (ML) to autonomously receive, authenticate, monitor, and secure delivery, return, and exchange of parcels. The system includes a parcel receptacle equipped with a removable and upgradeable IoT enclosure housing cameras, sensors, processors, communication modules, and power components, wherein AI and ML models analyze images, video, sensor data, contextual signals, and external data sources to identify delivery events, authenticate delivery personnel, detect anomalies, predict delivery windows, and dynamically control access mechanisms. The platform supports edge and cloud-based intelligence, authenticated integrations with carrier and e-commerce systems, location awareness, and real-time user interaction via networked devices. By combining modular hardware design with adaptive AI-driven decision making, the invention provides a scalable, future-proof secure delivery infrastructure that improves reliability, automation, and security of unattended parcel handling across residential, commercial, and multi-unit environments.

The present invention relates to a method and a device for controlling the steering of a vehicle, wherein the vehicle has a steering assistance system which, when activated, allows the vehicle to follow the lane being traveled and thus performs lane guidance by using a video sensor to determine the curvature of the road ahead of the vehicle;and, depending on the detected track curvature, the vehicle's steering is controlled in such a way that, depending on the vehicle's current speed, the steering actuator is controlled so that the vehicle continues to travel approximately in the center of the lane, whereby the control signals issued to the steering actuator are limited so that they are less than or at most equal to a predetermined curvature threshold, and if it is detected that a curve curvature must be adjusted for lane guidance, the control signals for which are above the predetermined curvature threshold, these control signals with a greater curve curvature are only issued to the steering actuator if the greater curve curvature has been validated using data from a digital map and the current location.