The invention discloses a rice lodging monitoring method using a thermal infrared image. The method is as follows: 1, farmland image acquisition, to be more specific, fixed point acquisition by an unmanned aerial vehicle (UAV) carrying thermal infrared imaging equipment; 2, characteristic value extraction, to be more specific, extraction of a color characteristic value, a texture characteristic value and a temperature characteristic value of a target area by image analysis tool Matlab; 3, construction of a lodging region discrimination model, to be more specific, training of the rice lodging discrimination model by the characteristic values extracted by the step 2 and known lodging conditions; 4, calibration of the lodging discrimination model, to be more specific, collecting of more lodging rice and non lodging rice samples for calibration of the lodging discrimination model trained in the step 3; and 5, verifying of the lodging discrimination model, to be more specific, verifying ofthe lodging discrimination model calibrated by the step 4 by an independent sample. The method uses the thermal infrared image to identify the difference between a lodging area and a non lodging areaof rice, and provides an effective means for lodging monitoring of the rice.

Rice lodging monitoring method using thermal infrared image

The invention discloses a potato defect detection and recognition system design based on machine vision. The potato defect detection and recognition system design is characterized in that defected potatoes are identified and classified on a ZYNQ platform by utilizing a machine vision library Open CV of an embedded Linux system; characteristic factors of the defected potatoes with green peels, dry rot, crust and mechanical damages are extracted and R, G and B discrete degrees of variable defect factors are analyzed to realize detection and recognition of surface defects of the potatoes, and the algorithm precision is greatly improved. Wavelet transform is applied to analysis and detection of potato shapes of the potatoes, and ellipse radiuses of the potatoes are extracted and are subjected to normalization processing; grading is carried out through a RBF (Radial Basis Function) neural network, so that the efficiency and precision of recognizing the defected potatoes by grades are improved; potato images are pre-processed by utilizing an FPGA (Field Programmable Gate Array) and an algorithm in the Open CV is subjected to accelerated processing; a calculation speed and the algorithm efficiency are remarkably improved. A testing result shows that compared with an existing defected potato recognition and classification technology based on software image processing, an image processing algorithm is innovated and optimized by a novel method based on a hardware structure platform, and the processing speed and the algorithm efficiency are greatly improved; theories and experiments show that the design has relatively ideal detection efficiency and speed on the recognition and classification of the defected potatoes in an actual process. The design has very great significance on a potato processing industry.

Potato defect detection and recognition system design based on machine vision

The invention puts forward a potato surface defect detection method based on a convolutional neural network. Colored images of potatoes are obtained by industrial cameras, and an image processing module is used for conducting analysis processing on the obtained images. The method is characterized in that the convolutional neural network is adopted for detecting the surface defects of the potatoes,a training set serves as a sample for training the convolutional neural network, then a prediction set is input to the network after training, and a softmax classifier is adopted for achieving classification of the potatoes. According to the method, feature extraction is not required, there is no need to set specific detection algorithms according to defect types, the images are directly input tothe network, and therefore the potato surface defect detection method has the advantages of being high in accuracy, short in algorithm running time, high in feasibility and robustness and the like, and has a significant meaning in the potato processing industry.

Potato surface defect detection method based on convolutional neural network

The invention discloses a multilayer information monitoring early warning method of early diseases of crops. The objective is to provide a lossless monitoring method of early diseases of crops. The method comprises steps of shooting the whole crop to obtain an object infrared image; calculating the average temperature of a monitoring object pixel point, the average temperature of a low-temperature pixel point and the average temperature of a high-temperature pixel point, and calculating the temperature difference between the average temperature of the low-temperature pixel point and the average temperature of the high-temperature pixel point; comparing the temperature difference with a monitoring threshold value and taking the temperature difference as the basis for determining whether the crops are infected with diseases; using a visible light-near infrared high spectral imaging device to monitor the crops suffering the diseases to obtain characteristic images; using a microscopy imaging device to monitor disease speckles in the characteristic images,= to obtain microscopy images; and according to a microscopy image gray scale histogram, estimating the early disease degree of the crops by combining the characteristic images. According to the invention, multilayer information of temperatures, pigments and textures of the crops is monitored; and disease detection and precise analysis in the incubation period and at the disease early stage are achieved.

Multilayer information monitoring early warning method of early diseases of crops

The invention discloses a method for detecting a mosaic disease of tomatoes in an incubation period through combination of infrared thermal imaging and near infrared spectroscopy, and relates to the technical field of detection of the mosaic disease of the tomatoes. According to the method for detecting the mosaic disease of tomatoes in the incubation period based on combination of the infrared thermal imaging and the near infrared spectroscopy, detection on biological information of crop diseases through the near infrared spectroscopy has a better effect, and internal structures and motion states of molecules can be directly reflected; a diagnosis and evaluation model of the incubation period of tomato diseases based on the infrared thermal imaging and the near infrared spectroscopy is built, and the method has intuitive property on important information such as lesion locations and area size. Compared with a conventional method for detecting diseases through a near infrared technology, the method disclosed by the invention has the advantages of high detection speed and early discovery; compared with a single near infrared spectroscopy means, the method disclosed by the inventionhas the advantages that the obtained information is more accurate, and the accuracy and the stability of a detection result are improved.

Method for detecting mosaic disease of tomatoes in incubation period through combination of infrared thermal imaging and near infrared spectroscopy

The invention discloses an early tobacco virus disease detection method based on an infrared thermal imaging technology, which comprises the steps that a tobacco infrared thermal image is subjected to image intensification from image smoothing, image sharpening and histogram equalization; a new tobacco leaf thermal image area and an old tobacco leaf thermal image area are extracted by a threshold segmentation method; if a temperature of a growth environment of tobacco is higher than 16 DEG C and less than or equal to 28 DEG C, a difference value between temperature values of various pixel points in the new tobacco leaf area and an average value of the temperature values is calculated; when an absolute value of the difference value is greater than 1 DEG C, a plant is a disease plant; if not, the plant is not the disease plant; when the environment temperature is higher than 28 DEG C and less than 34 DEG C, a difference value between average temperatures of the pixels in the new tobacco leaf area and the old tobacco leaf area is calculated; when the difference value is less than 0.8 DEG C, the plant is the disease plant; and if not, the plant is not the disease plant. The method is simple in step, short in consumed time and high in accuracy, can detect a disease earlier, can be applied to long-distance real-time monitoring of a field crop, and provides timely and reliable information of a crop growth condition, a disease condition and the like.

Early tobacco virus disease detection method based on infrared thermal imaging technology

The invention discloses a potato defect detecting method. According to the potato defect detecting method, a thermal imaging technology is used for rapidly recognizing peeled potatoes which are damaged, rot and sprout, and the thermal image processing processes of a computer are as follows: carrying out median filtering or average filtering and noise reduction on thermal images, extracting the regions of the potato thermal images by adopting a threshold value segmentation method, calculating the average temperature values of pixels in the regions, then calculating the difference value between the temperature value of each pixel in the regions and the average temperature value, and calculating the areas S of real objects to which the pixels with the absolute values of the difference values being greater than 1 DEG C, if S is greater than 25mm , the potatoes are defective. The potato defect detecting method disclosed by the invention has high efficiency and good recognition accuracy and can be popularized and applied to the field of potato defect detection.

Tian Guihua

Papers

Early tobacco virus disease detection method based on infrared thermal imaging technology

Potato defect detecting method