44 results about "Vision processing unit" patented technology

A safety monitoring system for a workspace area. The workspace area related to a region having automated moveable equipment. A plurality of vision-based imaging devices capturing time-synchronized image data of the workspace area. Each vision-based imaging device repeatedly capturing a time synchronized image of the workspace area from a respective viewpoint that is substantially different from the other respective vision-based imaging devices. A visual processing unit for analyzing the time-synchronized image data. The visual processing unit processes the captured image data for identifying a human from a non-human object within the workspace area. The visual processing unit further determining potential interactions between a human and the automated moveable equipment. The visual processing unit further generating control signals for enabling dynamic reconfiguration of the automated moveable equipment based on the potential interactions between the human and the automated moveable equipment in the workspace area.

Disclosed is a rotor unmanned aircraft independent take-off and landing system based on three-layer triangle multi-color landing ground. The system comprises a small rotor unmanned aircraft (SRUA), an onboard sensor, a data processing unit, a flight control system, an onboard camera, landing ground, a wireless image transmission module, a wireless data transmission module and a ground monitor station, wherein the onboard sensor comprises an inertial measurement unit, a global positioning system (GPS) receiver, a barometer, an ultrasound device and the like, the data processing unit is used for integrating sensor data, the flight control system finishes route planning to achieve high accuracy control over the SRUA, the onboard camera is used for collecting images of the landing ground, the landing ground is a specially designed landing point for an unmanned aircraft, the wireless image transmission module can transmit the images to a ground station, the wireless data transmission module can achieve communication of data and instructions between the unmanned aircraft and the ground station, and the ground station is composed of a visual processing unit and a display terminal. According to the rotor unmanned aircraft independent take-off and landing system based on the three-layer triangle multi-color landing ground, the reliability of SRUA navigation messages is guaranteed, the control accuracy of the SRUA is increased, costs are low, the application is convenient, and important engineering values can be achieved.

A dynamic range (D-range) compression apparatus that uses a look-up table (LUT) is capable of dynamic compression that compresses the peak input value to the full output range, even when image signals with variable D-ranges are inputted.

According to this D-range compression apparatus, D-range compression processing that places the D-range of the image signal within a predetermined output D-range is performed by the visual processing unit converting the tone of the image signal in accordance with the surrounding average luminance signal. Furthermore, with this D-range compression apparatus, the image signal is amplified in accordance with amplification input/output conversion characteristics determined based on the peak value in the image detected by the peak detection unit, and therefore it is possible to perform a dynamic amplification processing in accordance with the peak value so that the D-range of the image signal outputted from the visual processing unit becomes a predetermined output D-range.

The invention discloses an automatic assembling system and method and belongs to the technical field of sleeve assembling. The system comprises a visual collecting unit, a visual processing unit, a system control unit and an assembling unit. The method includes the following steps that firstly, the visual collecting unit is used for collecting and outputting first image information of a sleeve and second image information of a casing pipe to be operated; secondly, the visual processing unit is used for positioning the casing pipe to be operated according to the second image information; thirdly, the system control unit is used for locking the sleeve to be operated according to the first image information and the casing pipe to be operated, and outputting a grabbing instruction for sleeve grabbing; and fourthly, the assembling unit is used for grabbing the corresponding sleeve according to the grabbing instruction output by the system control unit and assembling the sleeve on the casing pipe. According to the technical scheme, the automatic assembling system and method have the beneficial effects of reducing labor cost in the assembling process, accelerating assembling progress and guaranteeing the automatic assembling accuracy rate.

The invention discloses a scraper knife posture control system and method based on machine vision and a land leveler, and belongs to the technical field of land levelers. A scraper knife can be automatically adjusted to a set posture according to an operation instruction of a driver, and the control difficulty and labor intensity of the driver are reduced. The scraper knife posture control system comprises a plurality of cameras, a visual processing unit and a vehicle-mounted controller, wherein the cameras are installed at set positions of the land leveler and used for collecting real-time position information of a plurality of visual perception tracking points installed at the set positions of the land leveler; the visual processing unit is used for acquiring the current posture of a scraper knife according to the received real-time position information of each visual perception tracking point, and generating a target state of a scraper knife posture control mechanism in combination with the target posture, sent by a man-machine display, of the scraper knife; and the vehicle-mounted controller is used for controlling the scraper knife posture control mechanism through an electric proportional control valve according to the target state and the current state of the scraper knife posture control mechanism, so that the scraper knife posture control mechanism drives the scraper knife to a target posture.

The invention relates to a satellite electric connector plugging examination system and method based on machine vision. The satellite electric connector plugging examination system based on the machine vision comprises a light source, an imaging part, a sensor, an image acquisition card, a visual processing unit, a control unit, a data processing unit, a database and a UI interactive processing unit. The problem of implementation of satellite electric connector plugging examination by adopting a machine vision system is solved so that reliability, real-time performance and safety of the satellite electric connector plugging examination link can be enhanced, and complexity and difficulty of the satellite electric connector plugging examination link can be reduced.

The invention discloses a water surface garbage autonomous collection method and a system thereof. The method comprises the steps of enabling an electronic module to be installed on a power ship for collecting water surface garbage, carrying out the autonomous recognition of a water surface object through a camera unit, and judging whether the garbage collection operation is carried out on the water surface object or not, using the camera unit, a visual processing unit, a sensing unit and a central control unit for autonomously avoiding obstacles and sweeping garbage on the water surface alongthe shore, establishing a three-dimensional model of a water area shoreline, and storing the information of the water area where the power ship works in the storage unit, monitoring the garbage collection amount in real time through the sensing unit, and when the garbage amount reaches a preset threshold value, enabling the power ship to automatically return. By the adoption of the water surfacegarbage autonomous collection method, autonomous recognition is conducted on the objects on the water surface through the camera unit, and garbage collection, autonomous obstacle avoidance, real-timemonitoring and automatic return are conducted on the objects on the water surface through the central control unit.

The invention discloses a ping-pong ball trajectory tracking device and method based on deep learning. The device comprises a posture sensing racket, a six-axis sensor, wireless transmission equipment, a first camera, a second camera, USB 3.1 transmission equipment, an FPGA, a visual processing unit, a central processing unit, a display screen, a memory, a GPRS module and network equipment. Two cameras capture table tennis pictures, the FPGA, the visual processing unit and the central processing unit are combined with the posture sensing racket to obtain a table tennis track, track analysis is conducted, the ball hitting condition of a player is obtained, the memorizer is used for storing data, the data is uploaded to the cloud through the GPRS module, and real-time checking is achieved. The three-dimensional position of the ping-pong ball is obtained in real time, the motion trail of the ping-pong ball is drawn, ball hitting conditions of players are analyzed, equipment is arranged in an embedded mode, utilized resources are small, and operation is easy and convenient.

The invention discloses a mechanical arm visual control device. According to the technical scheme, the mechanical arm visual control device is characterized by comprising a mechanical arm body, partition plates, a mounting base, a shifting mechanism, a first grabbing mechanism and a second grabbing mechanism, and a mounting cylinder with a mounting cavity is assembled at the tail end of the mechanical arm body; the partition plates are arranged in the mounting cylinder and divides the mounting cavity of the mounting cylinder into a first cavity body, a second cavity body and a third cavity body, and the first cavity body, the second cavity body and the third cavity body are all arranged to be fan-shaped cavity bodies; the mounting base is arranged in the center of the bottom of the mounting cylinder and located at the joints of the partition plates, a visual processing unit is mounted on the mounting base, and the visual processing unit comprises a visual sensor, a visual processor and a distance measuring sensor; the shifting mechanism is arranged in the first cavity and used for shifting parts into the grabbing range of the mechanical arm; the first grabbing mechanism is arranged in the second cavity and used for adsorbing and grabbing the parts; and the second grabbing mechanism is arranged in the third cavity and used for clamping and grabbing the part. The mechanical arm visual control device has the beneficial effects of being stable in grabbing and high in working effect.

The invention discloses an automobile vision switch control system. The system comprises an automobile main engine, a camera, a vision processing unit, and a vision control switch. During running, thecamera carries out real-time monitoring to obtain binocular dynamic features of a driver, the features are output to the vision processing unit, the vision processing unit generates a human eye dynamic digital model, on the basis of the model, binocular focal point high-frequency calculation is carried out, a determined human eye focal point space position is compared with space position of the vision control switch built in the vision processing unit, whether an equipment operator watches a certain vision control switch or not is judged, a judging result is output to the automobile main engine, the automobile main engine issues a control instruction to equipment, and vision control over the automobile function can be achieved. The blinking frequency or fixation duration serves as an instruction signal to be subjected to function control, and vision control is achieved.

An interactive image processing system including a first infrared camera, a second infrared camera, an image processing circuit, a vision processing unit, an image signal processor, a central processing unit, and a memory device is disclosed. The present disclosure calculates depth data according to infrared images generated by the first and second infrared cameras to improve depth quality.

A visual tracking system for tracking and identifying persons within a monitored location, comprising a plurality of cameras and a visual processing unit, each camera produces a sequence of video frames depicting one or more of the persons, the visual processing unit is adapted to maintain a coherent track identity for each person across the plurality of cameras using a combination of motion data and visual featurization data, and further determine demographic data and sentiment data using the visual featurization data, the visual tracking system further having a recommendation module adapted to identify a customer need for each person using the sentiment data of the person in addition to context data, and generate an action recommendation for addressing the customer need, the visual tracking system is operably connected to a customer-oriented device configured to perform a customer-oriented action in accordance with the action recommendation.

A variable configuration sensing, emitting, processing, and analysis system for various uses including but not limited to Virtual/Augmented/Mixed/Actual Reality imaging and tracking; Machine Vision; Object Identification and Characterization; First Responder Tracking, Diagnostics, and Triage; Environmental/Condition Monitoring and Assessment; Guidance, Navigation & Control; Communications; Logistics; and Recording. The variable configuration sensor, emitter, processor, and analysis system contains a housing and a mounting component adaptable to a variety of applications. The housing may include one or more sensors and/or emitters, vision processing units, micro-processing units, connectors, and power supplies. The sensors may include but are not limited to electromagnetic and/or ionizing radiation, distance, motion, acceleration, pressure, position, humidity, temperature, wind, sound, toxins, and magnetic. The emitters may include but are not limited to electromagnetic and/or ionizing radiation, sound, and fluids. The device may be ruggedized for use in extreme environments.

The invention belongs to the technical field of aerospace, and particularly relates to a rotor unmanned aerial vehicle visual carrier landing guiding method and system. Comprising an airborne intelligent terminal and a ground auxiliary identifier. The airborne intelligent terminal comprises a visual processing unit, a visible light camera and an infrared camera, and the visible light camera or the infrared camera is used for obtaining ground auxiliary identification image information in real time and sending the ground auxiliary identification image information to the visual processing unit; the visual processing unit compares the received image information with a target image library in the visual processing unit, obtains the speed quantity required by the landing of the unmanned aerial vehicle corresponding to the current image acquisition moment, and feeds back the speed quantity to the flight control system; the flight control system judges whether the current speed of the unmanned aerial vehicle meets the speed quantity required by landing of the unmanned aerial vehicle; according to the invention, based on visual servo control of the image, autonomous landing of the unmanned aerial vehicle under supervision control is realized.