48results about How to "Accurate detection and positioning" patented technology

The invention proposes an object detection and location method and system based on depth data. The method comprises the steps of acquiring a depth map by using depth data acquired by a depth data sensor, constructing a background model of the depth map, acquiring an object foreground region under the perspective of the depth map, and carrying out initial segmentation of the object foreground region; mapping the object foreground region after the perspective of the depth map to an overhead perspective by using a projection matrix, and segmenting the object foreground region under the overhead perspective again according to the location difference of an object in the horizontal space; extracting depth features of the foreground region, training an object detection module, and carrying out detection positioning for adhered objects by using the object detection module; and carrying out three-dimensional coordinate location correlation tracking for detection positioning results on an overhead map, mapping the detection positioning results to an original depth map coordinate, and obtaining a final object detection result. The invention can complete accurate object detection and location in a quick and robust manner under severely blocked and changing illumination conditions.

The invention, which is suitable for the machine vision field, provides a method and apparatus for measuring a vehicle distance and an automobile. The method comprises the following steps that: two cameras of a binocular vision system are used to collect images of scenes in front of a current vehicle synchronously; a candidate license plate region in the image collected by each of the cameras is obtained and a feature vector corresponding to each candidate license plate region is extracted; whether the candidate license plate region corresponding to each of the feature vectors is a real license plate region; a center position of the real license plate region is calculated; and according to the center position as well as a binocular stereo vision measurement principle, a distance between the current vehicle and a vehicle in front of the current vehicle is calculated. According to the invention, rapid and accurate detection and positioning on an automobile license plate in a complex background image is realized; and the distance between the current vehicle and a vehicle in front of the current vehicle in the vision angle range of the camera is calculated. The measurement range is large; and the measuring process can be realized simply and conveniently; and the performance for measurement is stable.

The invention relates to a low-power-consumption water level telemetering system based on an artificial intelligence cloud recognition water gauge. The system comprises a telemetering station, a central station server and a cloud server. The central station server is in communication connection with the client computer through a local area network or the Internet. The telemetering station comprises a network camera aligned with the water gauge, a telemetering terminal, a storage battery for supplying power, and a solar panel for charging the storage battery. The network camera collects imagesof the water gauge, saves the images and sends the images to the cloud server, the cloud server identifies the images and transmits water level data back to the telemetering station, and the telemetering station processes the water level data and sends the processed water level data to the central station server. The system is low in power consumption, low in cost and high in environmental adaptability; according to the invention, not only can quasi-water-level data be measured, but also images shot on site can be seen clearly, and manual data calibration on site is not needed any more throughimage comparison, so that the implementation effect is good.

The invention discloses a slideway type detecting positioning instrument which is used for detecting objects such as wood and metals hidden in walls during house decoration, maintenance, object installation and the like and positioning and marking detected objects. The instrument comprises a main ruler, two auxiliary rulers, an ultraviolet (UV) strip, a horizontal level gauge, a vertical level gauge, two sucking disc fixing devices, two sliding rails, a detector and a scriber, wherein a slideway groove and an UV strip groove are arranged on the main ruler, two auxiliary rulers are installed inside the slideway groove of the main ruler, the main ruler and auxiliary rulers are combined to form a slideway type detecting positioning instrument body, the UV strip is installed inside the UV strip groove of the main ruler, buckles are arranged on the horizontal level gauge and the vertical level gauge, sliding rail installation positions are arranged on the main ruler, two sliding rails are fixed inside sliding rail installation positions of the main ruler in an up-and-down mode, the detector and the scriber are installed on sliding rails, sucking disc fixing devices are arranged at two ends of the main ruler, the horizontal level gauge and the vertical level gauge are installed on two sides of the slideway groove, and sealing covers are arranged at two ends of sliding rails.

The invention relates to a video abnormal event detection method and a chip. The method comprises the following steps: acquiring a to-be-detected video; using the to-be-detected video to obtain at least two to-be-detected images arranged according to a time sequence; determining the spatial similarity between the adjacent to-be-detected images to obtain the spatial change feature of the to-be-detected video, wherein the spatial change feature comprises a change rule of spatial similarity according to a time sequence; determining the time sequence similarity between the adjacent to-be-detected images, and obtaining the time sequence change feature of the to-be-detected video, wherein the time sequence change feature comprises a change rule of the time sequence similarity according to a time sequence; fusing the spatial change feature and the time sequence change feature to obtain a fused change feature; utilizing a pre-trained detection model to determine whether the fusion change feature is abnormal or not; and if so, determining that an abnormal event exists in the to-be-detected video. According to the scheme, the video abnormal event identification efficiency can be improved.

The invention relates to an improved target object rapid detection method based on an SSD network. The improved target object rapid detection method is characterized by comprising the following steps:1) creation of an improved SSD network; (2) image data set acquisition, (3) network training and testing and (4) target detection. The method is scientific and reasonable in design, is suitable for the quick real-time detection of a target object, can reduce the network parameters, improves the network calculation efficiency, and is high in detection precision and speed compared with a standard SSD network.

The invention relates to an automatic wall-climbing type outer wall detection system. A roof track is fixedly arranged along the edge of a roof, a roof pulley capable of sliding along the roof track is arranged on the roof track, and a ground pulley is connected with the roof pulley through a flexible connecting part; a wall-climbing robot capable of moving up and down along the flexible connecting part is arranged on the flexible connecting part, the wall-climbing robot extends out of the wall surface to form a telescopic mechanical arm, and local detection equipment is arranged at the frontend of the telescopic mechanical arm. The system can achieve the comprehensive coverage of the outer wall of a building through walking arrangement, and safety and reliability are achieved; the localdetection equipment such as an ultrasonic detection instrument, a radar detection instrument, a knocking force hammer and a sound acquisition instrument can be selectively carried to realize large-area rapid automatic inspection of internal defects of an external wall external thermal insulation system or an external wall facing brick system.

The invention discloses a method and system for directly conducting remote detection on nonmetal pipelines, and belongs to the field of pipeline detection. The principle of the Doppler effect is applied, the pipeline detection technology of the brazing method, the two-point connecting method and the exclusive method are creatively adopted, the buried pipeline depth detection technology is also creatively adopted, the underground, underwater and overhead nonmetal pipelines can be accurately, rapidly and conveniently detected, and the method and system are particularly suitable for detecting the nonmetal pipelines such as buried PE pipes and cement pipes, and solve the problem that the nonmetal pipelines are hard to detect in the world at present. According to the three detection technologies, no connecting points on the pipelines need to be found, the problem that connecting points on the pipelines are hard to find through a traditional direct connecting method is solved, the detection range is greatly enlarged, and the target pipelines can be remotely and continuously tracked and detected.

The invention relates to a temperature effect based concealed wire detector and belongs to the technical field of electronic measurement. The temperature effect based concealed wire detector comprises a single-chip microcomputer, a temperature sensor array and a sound and light alarm device, the output end of the temperature sensor array is connected with the input end of the single-chip microcomputer, and the output end of the single-chip microcomputer is in control connection with the sound and light alarm device. Wall temperature changes are detected through the high-precision temperature sensor array according to the principle that concealed wires generate gentle heat in the process of energilization, and the sound and light alarm device is controlled to give an alarm when the temperature difference of sensors in the array is larger than a set value, and accordingly detection of the concealed wires in the wall is realized. The temperature effect based concealed wire detector is simple in structure, convenient to use, high in practicality, accurate in detection and positioning and small in error, and the problem that accurate positions of the concealed wires are difficult to search in building construction at present is solved.

The invention relates to the technical field of rail area equipment limit detection of rail traffic, and provides a positioning sliding trolley capable of automatically tracking the central line of a rail in real time. The positioning sliding trolley capable of automatically tracking the central line of the rail in real time comprises a trapezoid vehicle frame, wherein a first walking wheel is arranged at a left end beam of the vehicle frame, a second walking wheel and a third walking wheel are arranged at a right end beam of the vehicle frame, a middle longitudinal beam is arranged in the middle of the vehicle frame, two linear guide rails are arranged on the vehicle frame, a primary micro moving sliding block and a secondary micro moving sliding block are arranged on the two linear guide rails, a main shaft end portion of the first walking wheel penetrates out of a linear bearing hole embedded in the left end beam, a limiting retaining shoulder is arranged at the end portion of the main shaft end portion, a pre-tightening adjusting rod is arranged on the middle longitudinal beam, two pressure springs of the same rigidity are arranged between the limiting retaining shoulder and the primary micro moving sliding block and between the primary micro moving sliding block and the pre-tightening adjusting rod respectively, and the primary micro moving sliding block and the secondary micro moving sliding block are respectively provided with a detection device. By means of the positioning sliding trolley capable of automatically tracking the central line of the rail in real time, the walking wheels are attached to the steel rail, and efficient, continuous and accurate detection positioning of two different kinds of measuring bases is achieved.

The invention relates to a visual detection method for the assembling defects in a metal oxide arrester for electric power. In the visual detection method provided by the invention, a means that the electric measurement and the waveform observation are taken to be principal and the X-ray perspective radiation is taken to be auxiliary is adopted to realize the rapid diagnosis of the assembling defects in the metal oxide arrester for the electric power; the two ends of a discharge counter which is provided with an electric arrester are used for monitoring the voltage waveform through a common oscilloscope, and if the voltage waveform contains high-frequency and high-amplitude noise waves, the metallic suspended particle defect exists in the arrester; and by virtue of an X-ray perspective radiation means, the main point is that the visual expression of the structure feature in the arrester can be realized near the bottom of a single-section arrester, thereby directly determining that the defect exists in the arrester. The visual detection method provided by the invention mainly integrates an electric detection means and an X-ray perspective radiation technique to realize the rapid positioning and determination of the assembling defects in the metal oxide arrester for the electric power, and has the obvious advantages of concise structure, high efficiency, defect shape visualization and the like.

The invention relates to the technical field of network vulnerability detection, in particular to a network equipment vulnerability detection method, which comprises the following steps of: (1) IP scanning: scanning an IP network segment configured by network equipment; (2) routing detection: detecting IP addresses in an active IP list; (3) routing vulnerability scanning: judging whether the detected equipment has security weakness or not; (4) automatic vulnerability utilization: carrying out active vulnerability utilization on the network equipment with the vulnerability; (5) automatic decryption: decrypting a password detected via the vulnerability; (6) detection reporting: a complete detection report on detection results of a detected network segment is generated. Loopholes of the network equipment such as a router and a switch are automatically detected and accurately recognized, the detection time is greatly shortened, manpower and time are saved, and the safety of the network equipment is effectively improved.

The invention relates to a vehicle-mounted road positioning radar device with double-wave and an implementation method thereof, which is capable of detecting and positioning the precise position of the vehicle rapidly, accurately, repeatedly, and freely from environmental impact, and capable of transmitting data to a management platform through the mobile internet. The radar device comprises a radar positioning control unit, a communication unit, a power supply unit, a mobile phone application, and a passive digital sensor which is arranged in a related to-be-detected positioning subject object to receive energy from electromagnetic waves and capable of bi-directional communication. The radar positioning control unit comprises two groups of identical electromagnetic wave generating circuits and two groups of demodulation circuits thereof connected to an antenna A and an antenna B respectively, wherein the antenna A and the antenna B are arranged under the vehicle chassis; a control unit is composed of an ATmega8 single-chip microcomputer and a corresponding auxiliary circuit; the radar positioning control unit is connected to the communication unit and the power supply unit in sequence; the two inputs of the power supply unit are connected to the vehicle battery for supplying power thereto; and the mobile phone application is connected with the communication unit through a WiFior a Bluetooth wireless network.