Focused on the existing problems that there are few image datasets of citrus diseases and insect pests, the targets of diseases and pests are complex and scattered, and are difficult to realize automatic location and segmentation, a segmentation method of agricultural citrus disease and pest areas based on Superpixel Fast Fuzzy C-means Clustering (SFFCM) and Support Vector Machine (SVM) was proposed. This method made full use of the advantages of SFFCM algorithm, which was fast and robust, and integrated the characteristics of spatial information, meanwhile, it did not require manual selection of samples in image segmentation like the traditional SVM. Firstly, the improved SFFCM segmentation algorithm was used to pre-segment the image to be segmented to obtain the foreground and background regions. Then, the erosion and dilation operations in morphology were used to narrow these two areas, and the training samples were automatically selected for SVM model training. Finally, the trained SVM classifier was used to segment the entire image. Experimental results show that compared with the following three methods:Fast and Robust Fuzzy C-means Clustering (FRFCM), the original SFFCM and Edge Guidance Network (EGNet), the proposed method has the average recall of 0.937 1, average precision of 0.941 8 and the average accuracy of 0.930 3, all of which are better than those of the comparison methods.

For the increasingly severe parking problem, a method of parking lot space detection based on a modified convolutional neural network was proposed. Firstly, based on the characteristic that a parking lot only needs to be denoted by two states, a concept of Mini Convolutional Neural Network (MCNN) was proposed by improving the traditional CNN. Secondly, the number of network parameters was decreased to reduce the training and recognition time, a local response normalization layer was added to the network to enhance brightness correction, and the small convolution kernel was utilized to get more details of the image. Finally, the video frame was manually masked and cut into separate parking lots by edge detection. Then the trained MCNN was used for parking lot recognition. Experimental results show that the proposed method can improve the recognition rate by 3-8 percentage points compared with the traditional machine learning methods, and the network parameters of MCNN is only 1/1000 of the conventionally used convolutional model. In several different environments discussed in this paper, the recognition rate maintains above 92%. The experimental result shows that the MCNN can be transplanted to a low-configuration camera to achieve automatic parking space detection.