39results about How to "Easy to identify and handle" patented technology

The invention discloses an artificial intelligence-based unmanned aerial vehicle power transmission line inspection system and a method. The system comprises an unmanned aerial vehicle, a background server and an unmanned aerial vehicle control platform. The unmanned aerial vehicle acquires a target image according to a preset control instruction and transmits the target image to the background server. The background server receives the target image, performs image analysis, and sends the analysis result to the unmanned aerial vehicle control platform. The image analysis comprises the steps ofdefect automatic identification and forest hidden danger analysis. The unmanned aerial vehicle control platform is used for receiving a control instruction of an operator about the unmanned aerial vehicle, and pushing the analysis result to a shortcoming-eliminating team / group according to a confirmation instruction of the analysis result. According to the invention, the automation level of the line inspection and shortcoming-eliminating operation is improved. The false alarm rate and the missing report rate of manual identification and treatment are reduced. The accuracy and the effectiveness of the analysis are improved.

The invention provides an insect identification method and system. The system comprises a client and a server, the client is connected with the server, and the method comprises the following steps that the client acquires an image picture which is shot by a target user and contains an insect to be identified, acquires an insect region in the image picture, slices the insect region to obtain an insect picture, and sends the insect picture to the server; the server calls an insect type identification model deployed in the server to identify the insect picture, and sends an identification resultto the client; and the client pushes the identification result to the target user. By applying the scheme provided by the invention, the problems of high insect identification difficulty and low accuracy in the prior art can be solved.

The invention provides a method and device for text detection which are used for positioning a text region in a natural scene image. The disclosure relates to a text detection method and device and a text information extraction method and system. The method used for detecting a text region in an image comprises the steps of generating assemblies according to an input image; based on the similarity between feature values of any two assemblies, generating an assembly connector used for connecting the two assemblies; determining a main direction in allusion to each assembly connected by the assembly connectors to act as a main direction of each assembly according to direction distribution of the assembly connectors connected to each assembly; dividing the assemblies connected by the assembly connectors into at least one assembly group based on the difference between the main direction of the assemblies and a direction of the assembly connector used for connecting the assemblies; and generating a text region based on the at least one assembly group. Compared with the prior art, the method and device provided by the invention can position a text region in an image accurately, and the detection result can be further used for text recognition.

The invention discloses a night viewing image noise reduction method for an apple harvesting robot. The image noise reduction method for the apple harvesting robot comprises the steps that two night viewing images are collected consecutively with the same sampling position and the same angle through a camera in artificial light source, qualitative and quantitative analysis on noise containing in the night viewing images is conducted through a difference image method, and the noise type is judged that most of the noise is gaussian noise, and partial impulse noise is accompanied; according to the characteristics of the contained noise, firstly, the impulse noise and partial gaussian noise are removed through the use of a small valve soft threshold de-noising algorithm, and a lower gaussian noise image is acquired; maximum separation between image source signal and noise signal is conducted through the use of an independent component analysis method, and at that moment, the acquired image source signal contains partial gaussian noise; finally, noise reduction treatment is conducted on the image source signal through the use of the small valve soft threshold de-noising algorithm, and relative clean low-noise image is acquired. The night viewing image noise reduction method for the apple harvesting robot has the advantages that noise reduction function on the night viewing image is realized, preparation is made for the recognition of the night viewing image, and a foundation is laid for the further accomplishment of the night work of the apple harvesting robot.

The invention discloses a flatness inspection machine. The flatness inspection machine comprises a feeding transmission mechanism, a scanning detection mechanism, a column-dividing removing mechanism and a circular arranging mechanism and is characterized in that the feeding mechanism is provided with a feeding conveying belt, the conveying tail end of the feeding conveying belt is provided with a first column-dividing shaping mechanism, a laser displacement sensor is arranged above the end, close to the scanning detection mechanism, of the first column-dividing shaping mechanism, multiple flatness detection instruments are arranged above a scanning detection conveying belt, the conveying tail end of a removing conveying belt is provided with the removing mechanism, and a circular discharging mechanism is arranged on the other side of the conveying tail end of a circular arranging conveying belt. The flatness inspection machine is high in automation degree, high in measuring speed and high in measuring precision; multiple conveying belts and a shaping arranging mechanism can be used for carrying out position shaping and position correcting on the materials to be detected, the materials are automatically conveyed to the position below the scanning detection mechanism to be subject to surface flatness detection, and according to the detection result, the materials are subject to quality classification.

A manually inputting signal device, using locus groove to limit input locus. The checking process is easy. As it uses special locus groove layout program, it can directly map Arabic numbers, English letters, and quick-pen stokes. The user can easily and smoothly input all kinds of characters including Chinese characters with the help of quick-pen import law.

The invention discloses an image super resolution (SR) reconstruction method based on subspace projection and neighborhood embedding. The method is characterized by: using first and secondary subspace projection methods to project original high-dimensional data to a low-dimensional space, using dimension reduction feature vectors to show a feature of a low-resolution image block so that global structure information and local structure information of original data can be maintained; comparing a Euclidean distance between the dimension reduction feature vectors in the low-dimensional space, finding a neighborhood block which is most matched with the low-resolution image block to be reconstructed, using a similarity and a scale factor between the feature vectors to construct an accurate embedded weight coefficient so that a searching speed and matching precision can be increased; then constructing the similarity and the scale factor between the feature vectors, calculating the accurate weight coefficient and acquiring more high frequency information from a training database; finally, according to the weight coefficient and the neighborhood block, estimating the high-resolution image block with high precision, reconstructing the image which has the high similarity with a real object, which is good for later-stage real object identification processing.

The present invention discloses a method of perspective correction of iris image, suitable for execution in the mobile terminal, which includes: obtaining the original iris image of the user to be recognized;The location information of the human eyebrow membrane and its original iris image is calculated to obtain the viewing direction and horizontal angle θ of the human eye when the original iris image is obtained;The transformation matrix is converted to the three -dimensional space coordinate PS 'of the original iris image, and the three -dimensional space coordinate PS of the iris image after the correction is obtained.The invention also revealed a iris image perspective correction device and mobile terminal.

The invention discloses an artificial intelligence-based UAV transmission line inspection system and method. The system includes: a UAV, a background server and a UAV control platform, and the UAV collects target images according to preset control instructions. , and transmitted to the background server; the background server receives the target image, performs image analysis, and sends the analysis result to the UAV control platform; the image analysis includes: automatic defect identification and tree hidden danger analysis; UAV control The platform receives the operation instructions of the operator on the drone and the confirmation instruction for the analysis results, and pushes the analysis results to the defect elimination team. The invention improves the automation level of line inspection and defect elimination work, reduces the false alarm rate and missed alarm rate of manual identification processing, and improves the accuracy and effectiveness of analysis.