30results about How to "Suitable for identification" patented technology

The invention discloses a multi-people movement and breath detecting method based on a CSI signal in the Wi-Fi. The detecting method comprises the following steps that a CSI signal is extracted from the wireless signal of the indoor Wi-Fi, CSI signal data is acquired under the circumstance that nobody is in room, and CSI signal data of different movement postures and breath of human bodies at different positions in the room is acquired; preprocessing is carried out on all the CSI signal data; in the CSI signal data, movement data of human body breath is marked, which is used for constructing abreath identifying model; in the CSI signal data, human body posture data is marked, which is used for constructing a behavior identifying model; in the CSI signal data, according to CSI changes at different positions, monitoring areas are divided, and a space monitoring model is constructed.

The invention relates to the field of computer vision, and particularly relates to a vision-attribute-based X-ray security inspection contraband identification method by adopting a deep learning framework. The method comprises the following steps: 1) training samples are collected and labeled, original single-channel 16-bit high and low energy X-ray grayscale image are acquired, and through vision-attribute-based preprocessing, 16-bit three-channel color images are obtained as a data set for model training and testing; 2) the images in the training set are inputted to a network for training: adarknet network is used to extract features from the input image, a feature map is outputted, and a yolo layer is adopted to perform boundary frame prediction on the feature map at multiple scales, and after training, the model supports identification on already-labeled 12 categories of contrabands; and 3) images in a test set are inputted to the model for testing, identification results are outputted, the labeled contrabands are displayed on the input image, and according to IoU and R-P curves, mAP is calculated and obtained. Compared with the prior art, the method has the advantages of highaccuracy, high intelligence, high compatibility and the like.

The invention relates to the technical field of agriculture and particularly relates to a method for identifying heat-resistant seed setting performance of early rice at earing and flowering stages based on hour cumulative temperature. The method comprises the specific processes of labeling big ears about to be eared at the earing and flowering stages of the early rice, carrying out treatment for 6 hours at the constant stressing temperature of 38 DEG C at the time interval of 9: 30a.m. to 15:30p.m. every day, carrying out continuous treatment for 2 to 3 days, placing the early rice under natural conditions below the temperature of 32 DEG C and above the temperature of 25 DEG C at other time intervals, taking seed setting percentage under the natural conditions as a control, and adopting relative seed setting percentage as an index of the heat-resistant seed setting performance, thereby being capable of accurately and effectively identifying and distinguishing the heat resistance difference among early-rice variety materials. The method has the beneficial effects that by adopting the constant stressing temperature of 38 DEG C, the temperature of glumous flower tissue is about 36.2 DEG C and is slightly higher than thermal-damage critical temperature, i.e., the daily maximum temperature 35 DEG C of the earing and flowering stages of rice, so that the obtained seed setting performance of stress treatment is of obvious difference from that of the control and is in line with disaster damage performance of local short-time high temperature. The method is applicable to the identification on a large number of heat-resistant variety materials.

The embodiment of the invention discloses a road sign recognition method and device, a medium and a terminal, and the method can comprise the steps: obtaining a three-dimensional point cloud data setwhich comprises a plurality of three-dimensional point cloud data points obtained through the detection of a road; mapping the three-dimensional point cloud data set into a two-dimensional plane image; adopting a machine learning model to identify a road sign in the two-dimensional plane image; and inversely mapping the road sign in the two-dimensional plane image to a three-dimensional coordinateposition. The technical scheme in the embodiment of the invention is higher in accuracy.

The invention provides a video monitoring system and a real-time gait recognition method. In the process of image preprocessing, an extracted binary contour image is cut according to the minimum bounding rectangle thereof, and the image is scaled according to the maximum image height of all the image frames under the condition that the aspect ratio is kept unchanged. Therefore, all the preprocessed image frames are consistent in height, the aspect ratio before and after image processing is the same, and gait feature extraction is easier. According to the gait recognition method, both the static and dynamic characteristics of human gait are taken into account, the centroid height, the stride and the change rate of angular distance of the lower limb contour are extracted as gait features, and the gait differences of different individuals are comprehensively reflected. Through the method, the video monitoring system shortens the recognition time on the basis of ensuring high recognition rate. Moreover, the video monitoring system has better robustness to the clothing change of users, and is especially suitable for real-time user identity recognition in a video monitoring environment.

The invention relates to the field of crop planting, in particular to a method for identifying late rice head sprouting flowering period drought-enduring type varieties in field. The method comprises the following steps of 1) selecting a check variety, 2) sowing seeds and raising rice seedlings, 3) preparing the field, 4) conducting transplanting, 5) conducting drought treatment, and 6) identifying the drought resistance. According to the method, a late rice head sprouting flowering period variety comprehensive drought resistance formula is formulated, the check variety is set, the effect is easy to evaluate, the method is suitable for identifying a large number of drought varieties, the method is mainly used for identifying the drought resistance of the late rice head sprouting flowering period drought-enduring type varieties, the field simple identification method is adopted, and no complex instrument device is required.

The invention discloses a detection reagent and a typing method for the simultaneous genotyping of antigens of ABO blood group and specific A2, comprising four primers, two of which are sequential specific primers and the other two of which are inner comparison primers. The method can carry out simultaneous amplification to the blood group genes of the antigens of the ABO blood group and the specific A2 subtypes, which are very common among the Chinese population. The method can detect four alleles, A101, A102, B101 and O01, and six A2 alleles, A201, A202, A202, A204, A205 and A206, which are very common among the Chinese population. Compared with the traditional detection methods, the detection method of the invention is fast, simple, practical, specific and sensitive, is suitable for the genetic identification of ABO blood groups of Chinese Han population and can be used in the research of the ABO blood group of human beings.

The invention discloses a construction safety monitoring method and device based on machine vision, and the method comprises the steps: setting a plurality of peripheral monitoring devices around a construction region, and enabling the peripheral monitoring devices to comprise a visible light camera and an infrared camera; after the poses of the peripheral monitoring devices are initialized, aligning the poses of the peripheral monitoring devices with a construction area, sending pictures to the management platform, enabling a management platform to analyze the pictures through the neural network, and when abnormal personnel or objects enter the high-risk area, conducting recognition and alarm through the neural network. The invention is high in recognition rate and wide in application scene, and can automatically perform recognition and alarm.

The invention relates to a specific molecular marking primer and a method for identifying sarcandra glabra and three adulterants, belonging to the technical field of biology. In the method, a multiple-PCR system is established: total amount is 20mu L, 10ng of DNA is extracted from a plant to be used as an amplification template, 1*TransStart TopTaq DNA polymerase is added, 2mu L of 10*TransStart TopTaq Buffer is added, 2.5mM of dNTP is added, 0.2mu M of downstream primer and three upstream specific primers SgF, CspF and CsF which are respectively 0.1mu M in amount are added, and the rest is sterile water. The method is used for molecule identification based on genetic background, and is not influenced by external factors such as production places of medicinal materials; and compared with a chemical method, the method disclosed by the invention is more accurate, and is simpler and more convenient.

The invention relates to a traditional Chinese medicine (TCM) fingerprint establishment method, in particular to a radix salvia miltiorrhiza high-performance liquid chromatograph (HPLC) fingerprint establishment method and a radix salvia miltiorrhiza standard fingerprint obtained by adopting the method, provides a TCM fingerprint establishment method and a standard fingerprint, and aims to solve the problem that TCM substance identification and composition analysis can not effectively reflect and control the total body mass of TCM at present. The method comprises the following steps: firstly, preparation of a test solution; and secondly, high-performance liquid chromatograph analysis. The radix salvia miltiorrhiza fingerprint can be obtained by adopting the method. The method is used in the technical field of medicine analysis.

The invention discloses a fingerprint stamp pad, which comprises a pad cover, a pad base, an ink storage cushion and stamp-pad ink, and additionally comprises an ink control cushion, wherein the ink control cushion is arranged on the ink storage cushion, the stamp-pad ink comprises the components in percentage by weight: 10-20 percent of paint, 5-15 percent of water solube resin, 40-60 percent of humectant, 1-5 percent of emulsifying agent, 5-10 percent of thickening agent and the balance of water. The fingerprint stamp pad of the invention has simple operation and low cost, and can reach the effect of generalization and use. The success rate of fingerprint acquisition is high, non-professional personnel can also acquire the fingerprint image with clear lines and good quality, and the invention meets the requirements of input and identification of the automation fingerprint identification technology. The stamp-pad ink does not contain harmful substance, meets the requirement of environmental protection, and when being stuck on clothes and the skin, the stamp-pad ink is easy to clean, and can not hurt the skin.

The invention discloses a method for screening or identifying herbicide-resistant rice via agarose matrix. The method for screening or identifying herbicide-resistant rice via agarose matrix comprises the following steps: soaking the seed and sprouting, preparing the culture medium, sowing, observing and counting. The method is as follows: pouring 2L of the water into the electromagnetism pot, adding 10g of agarose, stirring evenly, boiling until that the agar dissolves totally, adding the herbicide imazethapyr mother liquor, the final concentration is 0.1ml/L, shaking evenly and pouring the mixture into the flat culture dish, using after that the culture medium solidifies; marking the name of variety on the culture dish, selecting the seed with stared area for 50-55 pieces, evenly sowing the seeds on the culture medium, sowing the resistant and anti-resistant variety for two pieces for having positive and negative contrast, scribing, separating and marking; observing and counting after 3-4 days. The method can screen or identify the herbicide-resistant imazethapyr rice quickly, effectively and exactly. Very good technical means is offered for the herbicide-resistant imazethapyr rice breeding and purity identification.

The invention discloses a molecular specific marker primer for identifying amaranthus viridis and two common adulterants and a method thereof, which belong to the technical field of biology. Accordingto matK gene sequences of amaranthus viridis, amaranthus albus and amaranthus retroflexus, an upstream specific forward primer is designed: AvF:5'-CTTTTTGTTCCTATATAATCTAG-3', AaF: 5'-CTAGTAAAAGTCAAAGTTAAGCG-3', ArF: 5'-GACTCAATTCTTCAGTAATACCA-3', and a downstream universal reverse primer matk-R: 5'-TATAATAATGAGAAAGATTTCG-3'. A multiplex PCR system and a fluorescent quantitative PCR reaction system are respectively constructed by utilizing specific primers, so that rapid and accurate qualitative and quantitative identification among amaranthus viridis, amaranthus albus and amaranthus retroflexus is realized.

The invention relates to a method and a device for detecting offset of a code spraying position. The method for detecting the offset of the code spraying position comprises the following steps that more than one marker are arranged on one side of a prefabricated code spraying position of a prefabricated part; the code spraying position is adjusted to be consistent with the corresponding prefabricated code spraying position; a marking material is sprayed to the markers; a detection device analyzes the reflection of the marks, and an alarm is given out if the offset exists; and according to theoffset condition, the spraying direction of spraying heads is adjusted. The method has the beneficial effects that the markers on one side of the code spraying position of the prefabricated part havea photosensitive function, and a detection part of the detection device is used for detecting the photosensitive markers; because the markers are of circular truncated cones or conical bulges, the detection part can identify the offset direction according to the color change of photosensitive parts on the bulges, and further fine-tune the position of the spraying heads; and because the detection is carried out according to the change of the photosensitive brightness, the arrangement of bulge structure makes the difference of the photosensitive brightness more obvious and the method is more suitable for staff to identify.

The invention discloses a transformer respirator detection method, a classification model construction method, a computer readable medium storing a transformer respirator detection program and a transformer respirator monitoring system, and belongs to the field of transformer detection. At least five characteristics of hue, saturation and brightness in an HSV color space, blue concentration offsetand red concentration offset in a YCbCr color space and the like are associated with non-failed colors and failed colors of the transformer respirator, so that the available state of the transformerrespirator is detected.

The invention provides an establishment method of a scorzonera fingerprint spectrum. The establishment method comprises the following specific steps: preparing a test solution by scorzonera, and carrying out fractionation detection under a certain condition by a high performance liquid chromatograph to obtain the scorzonera fingerprint spectrum. The invention further provides a scorzonera standard fingerprint spectrum obtained by the method. The standard fingerprint spectrum can provide reliable basis for scorzonera identification and internal mass control. The establishment method is simple and convenient to operate, high in stability, good in reproducibility and multiple in characteristic peaks. By utilizing the establishment method, the quality of scorzonera medicinal materials can be comprehensively and accurately evaluated.

The invention relates to the technical field of plant metabolomics, in particular to a method for comparing and distinguishing Wen country iron stick yam and other varieties of yam based on 1H NMR metabonomics technology. The method provided by the invention adopts H NMR-based metabolomics technology and uses principal component analysis (PCA) and orthogonal partial least squares discriminant analysis (OPLS-DA) to analyze the metabolites in the Wen country iron stick yam and the iron stick yam planted in other regions, and finally determines the difference between the metabolites between the Wen country planted iron stick yam and the iron stick yam planted in other regions, thereby providing a scientific basis for variety identification, true and false identification and the like of the Wen country iron stick yam as famous-region drug.

The invention provides a chicken individual identification method based on a VGG-16 convolutional neural network. The method includes collecting home chicken shadow image data by using a mobile cameraand intercepting a video corresponding to each individual into a picture by using Open CV according to a frame rate; changing the size of the picture into 100px * 100px by using a Python PIL toolkit,adding a prefix 1 _ to an output picture of the meadow chicken; adding a prefix 2 _ to an output picture of the white feather chicken; adding a prefix 3 _ to an output picture of the green-foot partridge chicken; 80% of the obtained domestic chicken individual pictures are used as a training set; taking 15% of the training set as a test set and 5% of the training set as a test set for subsequenttests, establishing a Keras convolutional neural network model, compiling a corresponding VGG convolutional neural network, adding the training set and the test set into the neural network, performingiterative training, and performing iteration for 10000 times to obtain a weight file; inputting a picture, and predicting the domestic chicken variety according to the weight file, so that the domestic chicken detection precision is effectively improved, and the method can accurately, efficiently and robustly detect the domestic chicken variety in a complex chicken farm environment.

The invention discloses a molecular specificity labeled primer for mutual discrimination of Amaranthus albus L., Amaranthus blitum L. and Amaranthus retroflexus L., and a method, and belongs to the technical field of biology. According to matK gene sequences of the Amaranthus albus L., the Amaranthus blitum L. and the Amaranthus retroflexus L., upstream specific forward primers AalF: 5'-TTTCAAAAAGGAATCGAAGATAA-3', AblF: 5'-CGAATCCATTTTTACGGAAACA-3' and AreF: 5'-GGGACTCAATTCTTCAGTAATACCA-3', and a downstream universal reverse primer matKR: 5'-AATAATGAGAAAGATTTCGGCAT-3' are designed. The specific primers are used for respectively building a multiplex PCR system and a fluorescent quantitative PCR system, and the fast and accurate mutual qualitative and quantitative discrimination among the Amaranthus albus L., the Amaranthus blitum L. and the Amaranthus retroflexus L. is realized.

The invention discloses a false target identification method and device and computer equipment, and the method comprises the following steps: obtaining at least one image, each of the at least one image comprising at least one to-be-identified target; when the number of the at least one to-be-identified target is greater than 1, extracting feature points of each to-be-identified target and performing feature point matching; and determining a real target and a false target group from the to-be-identified targets according to the feature point matching condition, wherein the real target and false target group comprises a real target and a corresponding false target. The whole method is small in calculation amount, high in recognition speed, suitable for human recognition and object recognition, and high in universality.