9results about How to "High recognition reliability" patented technology

The invention relates to the technical field of perception fusion, and discloses a tug fusion enhanced perception method based on target tracking and obstacle recognition, which comprises the following steps: processing an AIS, an optical fiber compass, a Beidou RTK, a laser radar, a millimeter wave radar and a panoramic camera on a tug to establish a ship coordinate system; and collecting message data of the AIS and combining with the MMSI information to screen the target ship to obtain the initial position of the target ship. And predicting the state sequence of the target ship to obtain the position, speed and heading information of the target ship. And carrying out target identification on the image, outputting identification results of semantic levels of the ship, the buoy and the quay wall, and carrying out space projection alignment with radar data. And fusing the processed results to obtain a fusion result, and performing early warning according to the fusion result. According to the method, the target ship relative pose resolving precision and the obstacle recognition reliability are improved, the sensing link time delay is shortened, and the driver blind area risk is reduced.

The invention provides a wall recognition method and a storage medium, and the method comprises the steps: dividing an indoor building region and a peripheral region, and processing the proportional scale information and wall feature information, so as to achieve the precise separation of the indoor building region and a peripheral irrelevant region, and prevent the interference information of the peripheral region from affecting the wall recognition process; automatic and accurate acquisition of the scale is realized by using natural reference scale features generally contained in a peripheral area, and extra manual labeling or intervention is not needed; vectorization data and thickness parameters of the wall are extracted in a targeted mode, and the integrity and accuracy of wall feature information are ensured; according to the method, the identification result of the wall is jointly determined based on the proportional scale information, the vectorized data and the thickness parameters, so that fusion application of multi-dimensional key information is realized, dimensions, forms and physical attributes required by wall identification are comprehensively covered, and the identification reliability in a complex environment is improved.

The invention provides a traffic signal lamp redundancy identification system and method based on red light narrowband filtering, and belongs to the technical field of intelligent driving environment perception. The system is characterized in that a main processing module processes a color image based on a YOLOv8n model and a lightweight convolutional neural network, and outputs a first recognition result and the confidence of the first recognition result; when the confidence coefficient is lower than a threshold value, a redundancy identification module is started, a narrow-band image obtained by an auxiliary imaging module is analyzed, whether a strong red light signal emitted by a traffic signal red light exists or not is judged through self-adaptive threshold value segmentation, morphological processing and feature analysis, and a second identification result is generated; and the decision fusion module fuses the two paths of results to generate a final control instruction. According to the invention, through physical spectrum filtering and double-path information fusion, interference of ambient light such as sunset and the like is effectively overcome, and the robustness and safety of an automatic driving system in recognizing traffic lights under complex illumination, especially red light, are remarkably improved.

This application discloses a method and device for identifying instability during the start-up phase of xanthan gum liquid film concentration. The method includes: introducing the same batch of xanthan gum liquid into the main membrane path and the shadow membrane path; after the first loading of the main membrane path, switching the main membrane path to a zero-permeability or near-zero-permeability holding section, and maintaining continuous flow in both the main membrane path and the shadow membrane path within the zero-permeability or near-zero-permeability holding section; determining whether the shadow membrane path has returned to the batch baseline recovery range based on the response of the shadow membrane path within the zero-permeability or near-zero-permeability holding section; when the shadow membrane path returns to the batch baseline recovery range, performing a second loading of the main membrane path; when the main membrane path deteriorates during the second loading, switching the main membrane path to zero net permeability, obtaining the main membrane path response information, and loading the shadow membrane path based on the loading trajectory of the second loading, obtaining the shadow membrane path response information; and identifying the instability type of the xanthan gum liquid based on the main membrane path response information and the shadow membrane path response information.

The invention relates to the technical field of reclosers, and provides an automatic recloser three-phase inrush current detection system and method. The system comprises a signal acquisition module, a sequence component calculation module, a feature extraction and trigger judgment module, a waveform cache module, a dynamic time warping core processing module and a decision output module. The method comprises the steps of collecting three-phase current and calculating negative-sequence current; when the negative sequence current exceeds a threshold value, intercepting a waveform as a to-be-detected sequence; calculating a dynamic time warping distance between the sequence and a pre-stored inrush current waveform template library; and judging inrush current or fault according to the minimum distance and outputting a corresponding signal. According to the method, negative sequence component characteristics and a dynamic time warping algorithm are combined, and the essential difference of the inrush current and the fault current in the overall form of the negative sequence component waveform is utilized for identification, so that the defects of poor adaptability and insufficient reliability in the prior art are overcome, and the method can effectively adapt to different transformer models, different closing conditions and changed system impedance; and the method has strong generalization ability and adaptability.

This invention provides a method and equipment for dynamically identifying extreme water-consuming zones in oilfields with ultra-high water cut, belonging to the field of oil and gas field development. The method includes: identifying extreme water-consuming oil wells and inefficient injection water wells; determining target oil wells from the extreme water-consuming oil wells whose inefficient water circulation level exceeds a preset value based on the cumulative water-oil ratio, and determining target water wells corresponding to the target oil wells from the inefficient injection water wells; determining the comprehensive slope comparison value of the target water wells based on the MHI index relationship curve, the cumulative apparent water absorption index curve, and the cumulative skin effect curve; and determining whether an extreme water-consuming zone is formed between the target oil wells and the target water wells based on the comprehensive slope comparison value of the target water wells. The method provided by this invention enables dynamic identification of different water-consuming zones, providing a basis for adjusting the inefficient injection circulation flow field in extreme water-consuming zones.

This invention discloses an FPV unmanned aerial vehicle (UAV) identification method and apparatus based on analog image transmission signals. The method includes: S1, setting acquisition parameter information, including acquisition center frequency and acquisition bandwidth; S2, acquiring spatial electromagnetic wave signals based on the acquisition parameter information to obtain an acquisition signal; S3, performing identification processing on the acquisition signal to obtain an identification signal.

The invention discloses a deep learning and machine vision fused intelligent identification method and system, and relates to the technical field of industrial visual defect detection, and the method comprises the steps: obtaining an original expanded grayscale image of a detected workpiece, and carrying out the normalization processing, so as to obtain image data with a unified brightness scale; determining the distribution of a highlight center based on the position with the highest brightness in each column, and intercepting a local gray sequence around the highlight center to calculate a brightness change boundary; comparing multiple columns of brightness change conditions to obtain reference data for reflecting a normal brightness change level, and forming a two-dimensional distribution diagram of the brightness deviation amount according to the reference data; and fusing the two-dimensional distribution map with a defect probability map generated by the deep learning model to obtain a comprehensive defect scoring map, and extracting a defect area based on a scoring result. According to the method, the tiny damage on the surface of the workpiece can be stably identified under the conditions of complex illumination and high reflection, and the detection precision is improved.

The present application relates to a kind of full-band beat vibration identification methods of rotating equipment, the method comprises: using vibration velocity sensor to collect the vibration velocity signal of rotor;Using variable mode decomposition VMD to decompose vibration velocity signal, obtain multiple intrinsic mode function;The FFT transform of all intrinsic mode functions is obtained, and corresponding frequency spectrum is obtained;While the analytic signal of all intrinsic mode functions is obtained after Hilbert transform, the corresponding amplitude envelope is obtained, and the FFT transform of each amplitude envelope is carried out, and corresponding envelope spectrum is obtained;Envelope spectrum is analyzed, and whether intrinsic mode function can be beat vibration signal is judged, and whether it is beat vibration signal is further determined after analyzing frequency spectrum, and excitation component is obtained.Compared with prior art, the present application can effectively avoid the uncertainty caused by subjective judgment, improve the robustness when tracing analysis, and realize full-band beat vibration detection under the condition of no rotation frequency prior.