65results about How to "Reduce the number of shots" patented technology

The invention discloses a binocular camera calibration method, device and system based on an Aruco code and a calibration board. The method comprises the steps: inserting an ArUco code calibration board into a white square block of a black-white checkerboard calibration board, so as to form a ChArUco calibration board embedded with the ArUco code; acquiring image information of a ChArUco calibration board during calibration, extracting corner point information of each black and white grid in the image information of the ChArUco calibration board, and forming corner point coordinates of the black and white grids; extracting ID information of each ArUco code in the image information of the ChArUco calibration board, and establishing a world coordinate system based on the ID information of each ArUco code; and carrying out binocular camera calibration according to the corresponding relationship between the image angular points of the target parameter points in the black and white grid angular point coordinates and the world angular points in the world coordinate system. The technical problems that a traditional binocular camera calibration method is low in success rate and inaccuratein calibration are solved.

The invention discloses a shooting method, a mobile terminal and a computer-readable storage medium. The method comprises: when a shooting instruction is detected, continuously shooting a plurality ofpictures, recognizing a person object for each picture in the pictures, cutting out a person object image in each picture, and forming a person object image group; measuring the sharpness of each ofthe plurality of pictures and measuring the sharpness of each of the person object images in the person object image group; selecting a picture with the highest definition as a target picture from theplurality of pictures, and selecting a person object image with the highest definition as a target person object image from the person object image group; replacing a person object image in the target picture with the target person object image, and displaying the replaced target picture. The invention can improve the clarity of the photographed person object image and reduce the photographing times.

The invention provides a vision-based multi-industrial-robot fault detection method and system. The vision-based multi-industrial-robot fault detection method comprises the following steps of S1, collecting a multi-industrial-robot standard operation video, establishing multiple single-industrial-robot standard operation mode video frame sequences A13, and executing S2; S2, acquiring a multi-industrial-robot operation video in real time, establishing multiple single-industrial-robot real-time operation video frame sequences A22, and executing S3; S3, matching a single-industrial-robot real-time action image with an image in a corresponding single-industrial-robot standard operation mode video frame sequence A13, detecting whether the single industrial robot acts abnormally or not by adopting a two-stage method, if so, executing S4, and if not, executing S2; and S4, controlling the industrial robot to stop suddenly. The method and the system have the advantages that sudden faults of anindustrial robot body are found in a non-contact mode, so that the safety accident that the robot hurts people during man-machine cooperation is avoided, and the detection process is simple and accurate.

The invention relates to an improved type auxiliary minimally invasive spinal surgical pathway positioning device. The improved type auxiliary minimally invasive spinal surgical pathway positioning device mainly comprises a fixed assembly, a transverse translational assembly, a longitudinal translational assembly, a lifting slide assembly, a longitudinal rotating assembly, a transverse rotating assembly and an angle indicating assembly. The fixed assembly is fixedly connected with a surgical bed or a trolley; a transverse positioning assembly can drive a rotating assembly and a longitudinal positioning assembly to conduct longitudinal translation; the longitudinal translational assembly can drive the lifting slide assembly and the rotating assembly to conduct transverse translation; the lifting slide assembly can drive the rotating assembly to adjust in the direction of a sliding rail; the longitudinal rotating assembly can drive the transverse rotating assembly to rotate along a rotary shaft; and the angle indicating assembly can indicate the rotating angle of the rotating assembly. The rotary shaft of the transverse rotating assembly is parallel to the translational direction of the transverse translational assembly which moves transversely, and a rotary shaft of the longitudinal rotating assembly is parallel to the translational direction of the longitudinal translational assembly. A first positioning ring and a second positioning ring which are used for supplying a guide needle to penetrate sequentially to position the transverse rotating assembly are arranged on the transverse rotating assembly, and the first positioning ring and the second positioning ring are spaced from each other and arranged concentrically. The centers of the two positioning rings are located on the rotary shaft of the longitudinal rotating assembly. The adjusting device can assist doctors to rapidly and accurately position the minimally invasive spinal surgical implantation pathway under the situation that the radiation frequency is low.

The invention discloses a power distribution facility switch detection and recognition algorithm based on deep learning, and the algorithm comprises the following steps: S1, collecting a photo of a to-be-recognized knob switch, and marking the position of the knob switch in the photo; S2, building a deep learning neural network by adopting a preset method, performing feature extraction on the marked photos, and storing a trained model; and S3, using the trained deep learning neural network model to recognize a to-be-recognized picture, and detecting the positions of the knob switch and the rotation center and the pointing point of the knob switch. The invention has the advantages that the position of the knob switch can be corrected, the number of times of photo shooting is reduced, the recognition efficiency is improved, even the knob switch on the edge of a picture can be recognized, the requirement for distortion of a camera is not high, the cost for purchasing the camera is reduced, in addition, the invention can be used for various occasions where the knob switch state needs to be detected. The state of the knob switch can be detected in real time, and alarm information is sent out when the state is abnormal.

Provided are an imaging device, an unmanned moving body, an imaging method, a system, and a program in which, even when there are few overlapping regions among images included in a telescopic image group, the telescopic image group can be excellently composed, and telescopic images can be composed with high precision, irrespective of a subject (scene) in a wide angle image. An imaging device (100)is provided with: an imaging optical system; a directional sensor; a wide dynamic range image generation unit (302) that generates wide-dynamic-range wide angle images obtained by enlarging the dynamic ranges of wide angle images; an image acquisition unit (2a) that acquires a wide-dynamic-range wide angle image group and a telescopic image group consisting of telescopic images; a composition information acquisition unit (2b) that analyzes the acquired wide-dynamic-range wide angle image group, and acquires composition information which is used for composition of the telescopic image group; and a composite image generation unit (2c) that generates an image by composing the telescopic image group on the basis of the composition information, information about the focal distances of a wide-angle optical system and a telescopic optical system, and the telescopic image group.