2782results about "Optical detection" patented technology

The invention provides a room obstacle detection optimization method and system based on a cross-modal attention mechanism. Wherein a dynamic compensation coefficient is calculated by acquiring motion track data of the mobile equipment, and a stable visual coordinate system is constructed. Visible light and near-infrared wave band acquisition of the multispectral sensor is synchronously triggered, the visible light captures geometric deformation characteristics of a floor projection surface, and the near-infrared detects a local heat radiation abnormal area. And extracting a thermal feature connected domain conforming to periodic biological motion as a living obstacle, and marking a collision risk boundary of a static obstacle. And based on a living body motion law and a collision boundary deviation trend, synchronously optimizing the dual-band exposure parameters and updating the trajectory prediction model, and forming a closed-loop feedback link of sensing and planning. According to the technical scheme provided by the invention, the living body and the static obstacle are accurately distinguished in a dynamic environment, and the sensor parameters are adaptively adjusted to improve the real-time obstacle avoidance response capability.

The invention relates to the technical field of track foreign matter real-time detection, and particularly discloses a track foreign matter real-time detection method based on YOLOv5 improvement. Comprising the steps of video vibration synchronous acquisition, space offset compensation parameter generation, dynamic feature enhancement processing, feature weight thermodynamic diagram generation, hierarchical perception feature aggregation, cross-scale target verification, foreign matter positioning instruction packaging and multistage early warning execution control. Image distortion caused by mechanical vibration and illumination fluctuation is effectively overcome by synchronously acquiring track video and vibration time sequence signals, constructing a spatial offset compensation parameter set and combining with a dynamic feature enhancement template to correct video frames, a feature weight thermodynamic diagram is generated through visual saliency detection, features are aggregated through a layered perception model, and the visual saliency detection accuracy is improved. Early warning levels are dynamically matched according to the sizes and the positions of the foreign matters, and a sound-light alarm and braking system is linked; according to the invention, the reliability of data transmission is ensured, the operation and maintenance cost is greatly reduced, and the safety requirement of millisecond response of modern rail transit is met.

The invention provides a mosquito detection and cooperative killing system and method.The mosquito detection and cooperative killing system comprises a bionic multi-mode sensor array and a dynamic feedback killing device, and the bionic multi-mode sensor array comprises an infrared sensing module used for simulating human skin radiation characteristics; the CO2 concentration gradient sensor is used for detecting the change of the concentration of carbon dioxide and activating the directional scanning of the infrared sensing module; the odor molecule release device is used for triggering a mosquito approaching behavior; the dynamic feedback killing device is used for starting the laser mosquito killing module and killing mosquitoes through infrared positioning coordinates. According to the technical scheme, the mosquito killing effect is improved.

The invention discloses a railway tunnel foreign matter detection method based on radar point cloud and RGB image fusion. The method comprises the following steps: acquiring a laser radar point cloud and an RGB image in a railway tunnel; obtaining an RGB image by using an adversarial network model GAN to judge the abnormal occurrence state of the foreign matter in the railway tunnel, and if the abnormal state of the foreign matter occurs, projecting the obtained laser radar point cloud to an image plane to obtain a dense depth map; processing through a sliding window to obtain data slices which are approximately square; and carrying out data feature extraction, fusion and foreign object target detection on the data slices of the RGB image and the dense depth map by using a fusion target detection network based on the OfficientNet-FPN, and outputting a foreign object target information detection result containing a target category, a position, a confidence coefficient and a distance. According to the railway tunnel foreign matter detection method based on radar point cloud and RGB image fusion, high precision, high efficiency and high reliability of railway tunnel foreign matter detection are realized.

The invention provides an underground structure boundary identification method and system based on distributed optical fiber sensing, and relates to the technical field of underground structure detection and boundary identification. The method comprises the following steps: firstly, arranging a sensing array in a to-be-detected area, establishing a channel corresponding to a space coordinate, and collecting a non-excitation base line; medium and noise are estimated through low-energy probe, excitation frequency band, energy and repetition rate are optimized, and the signals are emitted by an adaptive seismic source; reflection and transmission responses are synchronously collected under the unified time reference; performing wavelet denoising, temperature and dispersion compensation and time alignment on the data, and extracting amplitude, phase and frequency characteristics; gradient is calculated on the feature field, non-maximum suppression is carried out, and stable boundary points are obtained by adopting self-adaptive double thresholds based on local statistics and combining time continuity and space connectivity constraints; a two-dimensional section is obtained through spline fitting, a three-dimensional model is reconstructed under the constraint of multi-section consistency, a section map and the three-dimensional model are output, and high-precision, real-time and visual detection of small-size boundaries is achieved.

The invention relates to the technical field of laser heat treatment, and provides a calibration method of a full-automatic circuit board cutting machine. The method comprises the following steps: acquiring physical coordinates of a circuit board of a cutting device through an intelligent sensor, and constructing a reference coordinate system matrix based on the physical coordinates; determining vibration parameters of the cutting device according to coordinates of laser spots emitted by a laser and the reference coordinate system matrix, and generating a nonlinear error component according to the vibration parameters and power information of the laser; generating an error function based on an error matrix formed by the error components, and determining a calibration coefficient vector by solving the error function; closed-loop control is conducted on the laser path of the cutting device through the calibration coefficient vector, the adaptability of the cutting device to complex working conditions is improved by integrating multi-source error factors and establishing a nonlinear mapping relation, and the cutting precision and stability are ensured.

The invention provides a wheel tread derailment detection method and system for a railway vehicle. According to the method, jacking driving devices with jacking rotating wheels are symmetrically arranged on the two longitudinal sides of a track, a pressure sensing unit is arranged between the two jacking rotating wheels, optical detection units with orthogonal optical paths are installed on the outer sides, and displacement measurement units are integrated on the jacking rotating wheels, so that a three-dimensional detection network is formed. During detection, a top rotating wheel lifts a wheel step by step, a blocking signal, tread pressure and a vertical displacement parameter are synchronously collected, and a space mapping relation between a pressure decreasing path and a displacement abnormal point is established; converting the blocking signal into a blocking release rate, and calculating a displacement accumulated value in combination with a space mapping relation; and when the displacement accumulated value is continuously increased and the blocking release rate exceeds a threshold value, wheel-rail separation is judged, and jacking is controlled to be stopped. Through cooperative detection and analysis of multiple sensors, accurate judgment and self-adaptive jacking control of the wheel-rail separation state are achieved, and the problem of wheel diameter adaptability of a traditional fixed jacking mode is effectively solved.

The invention discloses an illumination adaptability rock crack identification and calibration method based on an image identification algorithm, and relates to the technical field of geotechnical engineering intelligent image identification, and the method comprises the following steps: collecting an illumination incident angle, a polarization state and an illumination gradient corresponding to an image frame, building an illumination time sequence observation layer, and obtaining an illumination time sequence observation layer; forming an illumination feature baseline for crack boundary tracking; and performing coherent phase decomposition on the image sequence based on the illumination feature baseline, stripping mirror reflection and enhancing diffuse reflection texture, and generating a crack drift suspicion image. Through construction of an illumination time sequence observation layer and coherent phase decomposition, illumination interference stripping in a crack image is realized, false drift is eliminated by combining anti-fact playback and time reconstruction, and a dynamic threshold control mechanism is constructed by introducing an anti-illumination mask and an anti-phase pattern and linking a polarized light diaphragm and a shading array. And high robustness of crack identification and closed-loop regulation and control of false early warning are realized.

The invention discloses an AI common mode inductance coil broken line material planting machine which comprises a first conveying line. A first material stripping module is arranged below the discharging end of the first conveying line. The m ejected inductance coils are grabbed by the first coil taking and placing manipulator and are transferred into the m bending jig grooves; the bending jig disc on the first transfer table is pushed to the feeding end of the second conveying line through a first jig disc push rod assembly; a T-core feeding device is arranged on the T-core feeding device; two pin bending machines; a second material stripping module is arranged below the second transfer table; and the discharging manipulator comprises an overturning manipulator and a rotating manipulator, the overturning manipulator is used for grabbing the m finished product materials and overturning the m finished product materials by 180 degrees, and the rotating manipulator is used for grabbing the m finished product materials overturned by 180 degrees, rotating the m finished product materials by 90 degrees and then discharging the m finished product materials to the material disc. According to the automatic feeding device, T-core magnetic core feeding, pin bending, finished product material overturning and material placing are integrated, and the inductance coil machining efficiency is improved.

The invention provides a target area monitoring method and device and a storage medium. The target area monitoring method comprises the steps that the staying duration of each object in a target area is monitored, and the target area comprises an isolation moving line and areas of preset ranges on the two sides of the isolation moving line; when it is monitored that the staying duration of a target object in the objects exceeds a preset time threshold value, monitoring the laser receiving condition of a target receiver in the set target area; and determining whether a target event occurs in the target area according to the laser receiving condition. Through the target area monitoring method, the behavior which can bring about the potential safety hazard can be found in time, namely, the occurrence of the target event is determined, and the efficiency and timeliness of finding the behavior which can bring about the potential safety hazard are improved.

The invention relates to a three-waveband off-axis reflective optical system with view field switching and focusing functions. Belongs to the photoelectric technical field. Multi-band common-caliber imaging is realized by adopting an off-axis two-reflection-path form, imaging information can be continuously obtained day and night all day, laser emitting and receiving capabilities are considered, and the device has functions of positioning aiming, laser guiding and the like. Large and small field-of-view switching imaging is realized through switching-in and switching-out of the secondary mirror, and the system has the capability of carrying out rapid search in a large field-of-view range and carrying out accurate identification and tracking in a small field-of-view range; the auto-collimation focusing of the optical system is realized by switching the position of the focusing mirror and arranging the focusing system, the system is ensured to be clear in imaging under the use conditions of different atmospheric pressures, temperature changes and photographing distances, and the system is suitable for accurate aiming and detection of a target under various complex and severe working conditions. The total reflection optical system is free of chromatic aberration, free of blocking, compact in structure and high in system integration degree, and the requirement for functional diversification of a photoelectric system is met.

The invention discloses a concept for improved position and orientation determination of a plurality of objects each marked with at least one optoelectronically detectable marker, in which holographic optical elements are introduced into two-dimensional flat markers, at which ambient light is reflected back with sufficiently high intensity even at high scattering angles relative to the surface normal of the two-dimensional flat markers.For this purpose, it is proposed to detect light reflected by holographic optical elements (HOE; 21, 22, 23) applied to the markers (20) in an optoelectronic sensor (32) and to generate a two-dimensional reflection image, and to detect, in an image processing device (34), on the basis of the spectrally resolved local intensity distribution of the two-dimensional reflection image detected by the optoelectronic sensor (32), differences between the reflection behavior of the optoelectronically detectable markers (20) of the current position and orientation of the plurality of objects (100; 200) and the reflection behavior of the optoelectronically detectable markers (20) in a reference configuration of the plurality of objects (100; 200), and to detect deviations in the overall configuration of the plurality of objects (100; 200) relative to the optoelectronic detection device (30) by evaluating the detected differences. determine.

The invention discloses an airborne low-detectability photoelectric long-distance stable tracking and aiming method based on a time-sensitive opposite target, and belongs to the technical field of airborne photoelectric detection and target tracking. The method comprises the following steps: step 1, target detection and miss distance calculation: in a level flight section of an airplane, imaging a target in a field of view, carrying out target detection by adopting an optical flow method, and detecting a moving target by analyzing a motion vector of pixel points in an image sequence; and resolving the deviation amount of the target image relative to the visual axis in real time, namely the target pixel miss distance. 2, designing a stable tracking loop: designing a two-layer control structure for the stable tracking loop, stably inhibiting high-frequency disturbance by a gyroscope of an inner loop, performing tracking correction on low-frequency deviation by an outer loop based on pixel miss distance, and finally realizing high-precision tracking. On the basis of real-time pixel miss distance feedback, a two-layer control structure is designed, the miss distance fed back by an outer ring tracking loop is converted into an inner ring control instruction, and the tracking precision and stability are improved.

The invention relates to the technical field of intelligent traffic, and discloses a method and device for detecting a thrown object on a road surface, and the method comprises the steps: automatically selecting the wavelength of infrared light according to the environment illumination intensity, and calculating an environment compensation coefficient; the infrared transmitting unit transmits a multi-angle light beam to the infrared receiving unit on the opposite side, and the infrared receiving unit determines the receiving state of the light beam; constructing a fan-shaped infrared beam grid, and determining an area where a suspected target is located; judging whether the suspected target is a thrown object or not, and using an area positioning model for the thrown object to obtain a central position and an effective area; implementing graded alarm; visible light image recognition is replaced by an infrared beam technology, the influence of severe weather on detection precision is effectively overcome through a self-adaptive wavelength selection mechanism, a specific lane where a thrown object is located can be accurately determined in combination with a lane recognition mechanism, and accurate guidance is provided for traffic control and cleaning operation.

The invention relates to a light curtain. The wiring workability under the condition that an operation indicating lamp is arranged on a light curtain of an optical synchronization system is improved. The light curtain includes a synchronization unit (optical axis for timing synchronization) for synchronizing the light projection timing of the light projector and the light reception timing of the light receiver by optical communication. A safety signal generated on the basis of whether or not an optical axis formed between the light projector and the light receiver is in a light-shielding state is output to the outside. The light curtain comprises a first operation indicating lamp arranged in the light projector; the second operation indicating lamp is arranged in the light receiver; an optical element (optical axis) provided in each of the light projector and the light receiver and configured to display the first operation indicator light and the second operation indicator light in conjunction with each other; and a control circuit configured to display the first operation indicating lamp and the second operation indicating lamp in linkage by using at least one group of optical elements.

The utility model relates to the technical field of optical fiber sensing, optical fiber communication and optical imaging, and discloses an image transmission device for discrete array light guide signal detection, which comprises an image transmission optical cable input end connector, an image transmission optical cable output end connector and an image transmission optical cable. According to the utility model, a plurality of light guide type annunciator or sensor output tail fiber end faces can be integrated, so that centralized image acquisition and signal transmission of annunciator or sensor array output signals are realized; there is no requirement for functional performance consistency between integrated light guide type or sensors; through the image zooming-in and zooming-out functions of the image transmission optical cable input end connector and the image transmission optical cable output end connector, the size of the image transmission optical cable can be reduced, and the application scene adaptability of the image transmission optical cable is higher. The integration level of a distributed measurement system based on a discrete light guide annunciator or a sensor array can be effectively improved, the complexity of the system is reduced, and the measurement efficiency is improved; parts are composed of full-passive optical devices, and the device has the advantages of being high in anti-interference performance and high in reliability.

The invention discloses a metro dangerous goods terahertz detection method based on adaptive downsampling and a multi-dimensional attention mechanism. The metro dangerous goods terahertz detection method comprises the following steps: acquiring a terahertz image data set; building a deep learning network model, wherein the deep learning network model comprises a backbone feature extraction network, a check feature extraction network, a down-sampling module, a fusion channel and space attention module, a space attention module and a YoloHead detection head which are connected in sequence; performing dual-path processing on the input feature map through parallel pooling and convolution operation; in the fusion channel and space attention module, global context modeling is carried out on the feature map; in the space attention module, long-range context dependence is captured through a strip-shaped pooling layer; inputting the multi-scale feature map output by the check network into a YoloHead detection head, and outputting a target detection frame; a redundant detection frame is removed through a non-maximum suppression algorithm, and a detection result with the highest confidence coefficient is reserved.

The utility model provides an SMT charging tray detection assembly, comprising a PCB circuit board, an emitter, a receiver, an isolation blocking structure and an opposite side light absorption blocking structure, the PCB circuit board is provided with a plurality of charging tray detection ends, and a charging tray grid is arranged between every two adjacent charging tray detection ends; each tray detection end is provided with a pair of matched emitter and receiver, the emitter and the receiver are respectively arranged at two ends of the same tray detection end, and the isolation blocking structure is arranged between the emitter and the receiver of the same tray detection end; one side of the charging tray detection end is provided with the opposite-side light absorption blocking structure, and the opposite-side light absorption blocking structure is arranged on one side, close to the mounting surfaces of the emitter and the receiver, of the charging tray detection end. The SMT tray detection assembly can well avoid the problem of false triggering, is easy to design and implement, can be continuously used, and effectively improves the actual use effect and the application range of the SMT tray detection assembly.

The invention relates to a powder detection method, system and device, a storage medium and a program product. The method comprises the following steps: determining a reference moving speed of a material carrying mechanism according to a signal coverage range of an electromagnetic wave generator and a preset moving time length of powder to be detected in the signal coverage range, and controlling the material carrying mechanism for carrying the powder to be detected to move according to the reference moving speed, controlling the electromagnetic wave generator to emit an electromagnetic wave signal to the to-be-detected powder at the position where the to-be-detected powder reaches the electromagnetic wave generator on the material carrying mechanism, and acquiring an infrared signal generated by the to-be-detected powder and received by the infrared detector at the position where the to-be-detected powder reaches the infrared detector on the material carrying mechanism; the detection result of the metal particles in the powder to be detected is determined according to the infrared signal; the electromagnetic wave signal is used for heating metal particles in the to-be-detected powder; according to the method, the detection sensitivity is improved, and the risks of missing detection and error detection are correspondingly reduced.

The invention provides a screen foreign matter detection device and method, and belongs to the technical field of optical detection, and the screen foreign matter detection device comprises an SPAD SoC chip, a VCSEL chip, a packaging substrate, a packaging cover plate, a first optical filter, a second optical filter, a transmitting lens, a receiving lens and a lens base. The mounting position of the foreign matter detection device is selected; selecting opposite sides; recording a fixed distance during initial installation; according to the method and the device, whether foreign matters exist on the surface of the screen or not is detected by adopting linear light spots according to the setting of a foreign matter detection judgment basis, and the method and the device have the advantages of small size, low cost and high precision, can be applied to foreign matter detection of an automobile HUD and other related fields with certain requirements on projection safety, enable the screen to be more intelligent and improve the overall safety.

The invention relates to a device (10a, 10b, 10c) for transporting electrically conductive connecting elements (12a, 12b) such as rivets or screws from a transmitting station to a receiving station, comprising a line (20, 20c) enclosing a transport channel (22, 22c) for the connecting elements (12a, 12b) and leading from the transmitting station to the receiving station, and comprising a first coil arrangement (24, 24c) with at least one first magnetic coil (26, 26c) for generating a first electromagnetic field in the transport channel (22, 22c), the windings of which coil circulate around a first section (28, 28c) of the transport channel (22, 22c), the first electromagnetic field inducing eddy currents in the connecting elements (12a, 12b) which accelerate the connecting elements (12a, 12b) in the direction of the receiving station.According to the invention, a second coil arrangement (30, 30c) with at least one second magnetic coil (32, 32c) is provided for generating a second electromagnetic field in the transport channel (22, 22c), the windings of which run around a second section (34, 34c) of the transport channel (22, 22c), which is arranged closer to the receiving station than the first section (28, 28c), wherein the second electromagnetic field induces eddy currents in the connecting elements (12a, 12b) which accelerate the connecting elements (12a, 12b) in the direction away from the receiving station.

The invention discloses a laser broken line rapid identification method for a spinning process, relates to the field of spinning detection, and is used for solving the problem of high identification error rate in a multi-material blending and frequent line changing environment. A multi-channel optical behavior characteristic matrix is formed by constructing a broken line recognition mechanism based on material perception and light intensity behavior characteristic collaborative modeling, collecting light intensity response data of yarn channels, constructing a dynamic detection sequence and extracting characteristics such as shielding amplitude gradient and recovery time delay. A yarn material identifier is introduced, a spectral response template is matched, a broken yarn judgment threshold group is generated, whether shielding sudden change and delay recovery characteristics are met or not is judged in combination with a detection sequence, a broken yarn event is accurately recognized, and recognition parameters are corrected in real time according to the shielding edge change rate and fluctuation stability in light intensity changes before and after yarn breakage. The dynamic optimization of the broken line judgment condition is realized, and the recognition precision and the response speed are improved.

Improvements in fluid volume measurement systems are disclosed for a pneumatically actuated diaphragm pump in general, and a peritoneal dialysis cycler using a pump cassette in particular. Pump fluid volume measurements are based on pressure measurements in a pump control chamber and a reference chamber in a two-chamber model, with different sections being modeled using a combination of adiabatic, isothermal and polytropic processes. Real time or instantaneous fluid flow measurements in a pump chamber of the diaphragm pump are also disclosed, in this case using a one-chamber ideal gas model and using a high speed processor to obtain and process pump control chamber pressures during fluid flow into or out of the pump chamber. Improved heater control circuitry is also disclosed, to provide added or redundant safety measures, or to reduce current leakage from a heater element during pulse width modulation control of the heater element. Improvements are also disclosed in an application of negative pressure during a drain phase in peritoneal dialysis therapy, and to control an amount of intraperitoneal fluid accumulation during the therapy. Improvements in efficiency are also disclosed in movement of fluid into and out of a two-pump cassette and a heater bag of the peritoneal dialysis cycler, and in synchronization of operation of two or more pumps in the peritoneal dialysis cycler or other fluid handling devices using a multi-pump arrangement.

According to the single-photon laser multispectral polarization detection method and system under underwater turbulence disturbance provided by the invention, pulse laser is emitted to a target after being scanned, and weak echoes of the pulse laser are received by a double-photon detector and a single-photon detector after being subjected to spectral filtering and spatial polarization beam splitting. A time correlation single photon counting technology is adopted, time, polarization and wavelength information of each photon is recorded synchronously, and a multi-dimensional data set is generated in combination with a scanning angle. After turbulence noise is suppressed through preprocessing, target distance information is extracted to generate a three-dimensional point cloud, and the polarization degree and the depolarization ratio of each pixel point are calculated; and finally, geometric, polarization and spectral data are fused, a high-precision three-dimensional terrain and polarization image is generated, and accurate target identification in a complex underwater environment is realized. According to the invention, a set of multi-dimensional information sensing system capable of carrying out long-distance, high-resolution and high-precision classification and identification on a target in a complex underwater environment with strong attenuation, strong noise and strong turbulence disturbance is constructed.

A method of determining at least one fluid interface in at least one annulus surrounding a tubing of a wellbore, the method comprising: providing a buoyancy module, floating the buoyancy module at the at least one fluid interface; generating an acoustic signal with an acoustic signal generator connected to the buoyancy module; detecting the acoustic signal with an optical signal carried within an optical fibre arranged in the longitudinal direction of the tubing.

The present application provides a method and device for window occlusion detection, which belongs to the field of sensor technology and can be used for assisted driving and autonomous driving. The method includes: obtaining a first window echo intensity and a second window echo intensity, the first window echo intensity represents the reference window echo intensity, and the second window echo intensity represents the window echo intensity at the current moment; obtaining the detection parameters of the target point at the first moment and the detection parameters at the second moment, the detection parameters including the reflectivity and / or position coordinates of the target point; according to the first window echo intensity, the second window echo intensity, the detection parameters at the first moment and the detection parameters at the second moment, obtaining a window occlusion parameter, the window occlusion parameter is used to indicate the window occlusion state. This method improves the accuracy of lidar window occlusion detection, so as to improve the terminal's advanced driving assistance system (ADAS) capabilities in autonomous driving or assisted driving.

The invention discloses iron core processing equipment, and aims to provide iron core oil hole connectivity detection equipment which is good in detection effect, high in detection efficiency and capable of accurately detecting the specific blockage position and a control method of the iron core oil hole connectivity detection equipment. When the material lifting mechanism reaches the detection mechanism, the iron core can penetrate through the detection groove body, meanwhile, the mounting plate abuts against a baffle of the detection mechanism, the lifting assembly continues to move, at the moment, the mounting plate is attached to the bottom plate under the action of the baffle of the detection mechanism, and the oil hole connectivity is detected. The detection rod on the bottom plate penetrates through the through hole to enter the oil hole of the iron core, if the oil hole of the iron core is blocked, the detection rod jacks up the iron core and blocks a signal of the infrared detection device, automatic detection of the iron core is completed, the lifting assembly retreats to complete resetting after detection is completed, the overall process is simple and convenient, and the iron core oil hole detection device is suitable for the technical field of iron core oil hole detection.