32results about How to "Not affected by light" patented technology

The invention discloses a method for recognizing a mobile robot by comparing images. The method comprises the following steps: lighting a shot area to be shot by a mobile robot by using a single color lighting unit; shooting a position image corresponding to the shot area by the mobile robot through a camera; acquiring a reference image corresponding to a route that the mobile robot passes by the mobile robot from a known position image; comparing the position image with the reference image by the mobile robot, adjusting the position image according to a comparison result, and overlapping images of same areas of the position image and the reference image; calculating positions of a corresponding shot area of the position image relative to a corresponding track reference point of the reference image, thereby confirming a track position of the mobile robot. By adopting the mode, the mobile robot disclosed by the invention is high in stability, simple in mounting program and low in design cost, and the user experience can be greatly improved.

The invention discloses a method for rapid degradation of triphenylmethane dye waste water. The method firstly removes impurities by a grill, stands for precipitation and regulates pH, wherein, the pHvalue of the triphenylmethane dye waste water is controlled to be about 7-10; the waste water is introduced into a simple reaction container, then a mixture consisting of sodium bismuthate and silvernitrate is added, the multi-phase uniform mixing reaction is kept under the action of stirring, the temperature of the dye waste water during the process is kept at room temperature, the pressure isnormal pressure, and the waste water is discharged. The treatment method can high-efficiently degrade triphenylmethane dye which is typically difficult to biodegrade, the catalytic reaction can be realized without the use of any light source or other external energy, such as microwave and the like, and the treatment method has very low requirements on equipment, less energy consumption, low operation cost, convenient operation and no secondary pollution, thereby being the method which can realize the degradation at the room temperature.

The invention provides a cargo pallet detection method and system based on point cloud plane contour matching. The method includes the following steps: S1, original point cloud filtering; S2, point cloud plane segmentation; S3, generating a grid map through projection; S4, contour extraction; S5, contour matching; and S6, acquiring the relative position and posture. The system includes an original point cloud filtering module, a point cloud plane segmentation module, a module for generating a grid map through projection, a contour extraction module, a contour matching module, and a relative position and posture acquisition module. The method and the system are of low cost and high detection accuracy, and are basically not affected by illumination. There is no need for label laying or other operation, and there is no need to transform the storage environment. The method and the system are suitable for pallets of various colors and specifications, and have the advantages of high accuracy, low price, strong robustness, and the like.

The invention discloses a sensing carpet, a system and a method used for monitoring pedestrian flow density in a public place. The monitoring of the pedestrian flow density is realized through the communication between the sensing carpet and a monitoring terminal by taking the sensing carpet as sensing equipment of the pedestrian flow density. A sensing detection circuit of the sensing carpet mainly comprises a detection module, a communication interface and a plurality of compression detection devices arranged in the sensing carpet in arrays; the sensing detection circuit is simple in structure, low in cost and easy to realize; the sensing carpet can be paved in various public places at any time, can be used and installed immediately, and is very convenient to install, detach and move; and the monitoring terminal can be realized by any terminal with communication, data processing and display functions, can realize portable monitoring. The processing flow of the overall system is simple, the programming difficulties of software programming personnel are reduced, the hardware performance requirements on a sensing carpet detection module and the monitoring terminal are reduced, and both the manpower and resource cost of system development can be controlled effectively.

The invention discloses a human body identification method based on a sequence depth image, comprising: collecting the sequence depth image of a human body, and using a convolutional neural network and a recursive neural network to perform regression of human body joint points based on the sequence depth image to obtain the coordinate positions of the human body joint points ; Use the coordinates of the joint points of the human body to calculate the body posture feature vector, use the static feature classifier to identify, and obtain the human body identity recognition score of the static feature; extract the human body motion behavior feature from the sequence depth image, and use the dynamic feature classifier to perform Recognition to obtain the human body recognition score of dynamic features; the weighted calculation of the static and dynamic features of the human body recognition score to obtain the human body recognition score, and then obtain the human body recognition result. The present invention has strong robustness, and the accuracy rate is not affected by application scenarios.

The invention discloses a vehicle-mounted device having a driving complete period fatigue level real-time identification and early warning function. The device mainly comprises the following modules: a cumulative driving duration acquisition module which is used for judging the cumulative operation state duration of the vehicle and determining the cumulative driving duration of the driver; a workload acquisition module which is used for judging the high-speed driving cumulative workload of the driver; a GPS module which is used for accurately judging the current moment information; a circadian rhythm acquisition module which is used for judging the circadian rhythm cumulative degree of fatigue of the current driver through a moment information circadian rhythm table; a fatigue degree value calculation module which obtains the fatigue degree value of the driver of any moment; and an early warning module which is used for giving fatigue early warning information. According to the vehicle-mounted device, fatigue level judgment can be performed on any time period in the driving process so that the traffic accident can be reduced to a certain extent, the hazard caused by the traffic accident can be reduced and driving of the driver and public traveling are enabled to be safer.

The invention discloses a light-emitting diode display panel, a manufacturing method thereof, and a display device, and relates to the field of display technology. The light emitting diode display panel includes a thin film transistor backplane and a light emitting structure, and the light emitting diode display panel further includes a protective film, the protective film is located between the thin film transistor backplane and the light emitting structure, and the protective film covers The LED display panel displays gate lines and data lines in the display area. The protection film also covers the circuits around the display area of ​​the LED display panel. The present invention adds a protective film process to the manufacturing process of the existing light-emitting diode display panel, which can effectively prevent the scratching of the thin-film transistor backplane by the evaporation mask and the static electricity problem caused by the evaporation mask when making the light-emitting structure.

The invention discloses a multi-strategy anti-fraud face recognition method, comprising: Step 1. During the face detection process, detect whether there is a bright pupil generated by a near-infrared device at the position of the pupil of the eye, and detect the gray level of the skin color of the face at the position of the face In the interval, whether the variance meets the threshold, and judge whether it is a fraudulent attack; step 2, according to the dynamics of the face recognition process, in the face recognition verification process, based on the 3D face reconstruction of the Candide‑3 model, micro-expression detection is performed, Compare the similarity between the facial features and the 3D model between the adjacent 3 frames, and set a reasonable threshold to avoid overly similar faces.

The application discloses an array substrate, a manufacturing method thereof, and a display panel. In this application, the source pattern and the drain pattern are designed to be directly formed on the dielectric layer, and the traditional flat layer and passivation layer are replaced by the dielectric layer, and the drain pattern is also used as the anode pattern of the OLED device, thereby reducing the The photomask process, and the dielectric layer is made of a light-shielding material, which can protect the channel layer of the TFT from being affected by light, and is beneficial to ensure its stable performance.

The invention provides a composite processing device and a composite processing method. The compound processing device includes: an additive manufacturing part, which irradiates energy to the workpiece in the processing area to perform additive manufacturing; a cutting processing part, which cuts the workpiece in the processing area; a cover part, covering the processing area; The light-shielding filter is arranged on at least one surface of the cover portion, and changes the light-shielding degree according to the light received from the processing area.