2results about How to "Uniform Image Quality" patented technology

The invention discloses a range gating imaging system based on pulse phase shift. Comprising a digital control unit used for generating M laser pulse signals and shutter control signals, M laser driving modules, M groups of laser diodes, and an optical fiber beam combiner used for combining laser output by each group of laser diodes, the imaging unit receives a shutter control signal and comprises an image intensifier and a driving module thereof, and the image intensifier and the driving module are used for performing gating imaging on a target under the control of the shutter control signal; wherein M is greater than or equal to 2, repetition frequencies of the laser pulse signals are the same, but phases have difference values; each laser driving module is connected with a laser pulse signal output end of the digital control unit; and each group of laser diodes is connected with one laser driving module, and each group of laser diodes outputs laser under the driving of corresponding laser pulse signals.

The present application relates to pipeline nondestructive testing image recognition technical field, specifically to pipeline internal defect intelligent detection method based on image recognition, including: through endoscopic equipment gathers pipeline internal surface annular scanning image sequence, obtains the feature map set containing potential defect area through image preprocessing and multilevel feature extraction;Defect candidate region is generated by using improved attention guide network to complete feature fusion and defect candidate region focusing processing, and the weighted feature expression of the candidate region is generated;Through defect morphology analysis and classification discrimination, output defect category label and morphology parameter, and generate comprehensive defect evaluation report combined with pipeline structure information.The method is suitable for pipeline annular structure to realize global continuous acquisition, eliminate detection blind area, strengthen defect features through attention weighting, suppress redundant background interference, improve defect positioning accuracy and classification accuracy, and guarantee the integrity, accuracy and reliability of pipeline internal defect detection.