Automated Counting of Rice Planthoppers in Paddy Fields Based on Image Processing

A quantitative survey of rice planthoppers in paddy fields is important to assess the population density and make forecasting decisions. Manual rice planthopper survey methods in paddy fields are time-consuming, fatiguing and tedious. This paper describes a handheld device for easily capturing planthopper images on rice stems and an automatic method for counting rice planthoppers based on image processing. The handheld device consists of a digital camera with WiFi, a smartphone and an extrendable pole. The surveyor can use the smartphone to control the camera, which is fixed on the front of the pole by WiFi, and to photograph planthoppers on rice stems. For the counting of planthoppers on rice stems, we adopt three layers of detection that involve the following：（a） the first layer of detection is an AdaBoost classifier based on Haar features;（b） the second layer of detection is a support vector machine（SVM） classifier based on histogram of oriented gradient（HOG） features;（c） the third layer of detection is the threshold judgment of the three features. We use this method to detect and count whiteback planthoppers（Sogatella furcifera） on rice plant images and achieve an 85.2% detection rate and a 9.6% false detection rate. The method is easy, rapid and accurate for the assessment of the population density of rice planthoppers in paddy fields.

Improvement of registration accuracy of a handheld augmented reality system for urban landscape simulation

The need for visual landscape assessment in large-scale projects for the evaluation of the effects of a particular project on the surrounding landscape has grown in recent years. Augmented reality （AR） has been considered for use as a landscape simulation system in which a landscape assessment object created by 3D models is included in the present surroundings. With the use of this system, the time and the cost needed to perform a 3DCG modeling of present surroundings, which is a major issue in virtual reality, are drastically reduced. This research presents the development of a 3D maporiented handheld AR system that achieves geometric consistency using a 3D map to obtain position data instead of GPS, which has tow position information accuracy, particularly in urban areas. The new system also features a gyroscope sensor to obtain posture data and a video camera to capture live video of the present surroundings. All these components are mounted in a smartphone and can be used for urban landscape assessment. Registration accuracy is evaluated to simulate an urban landscape from a short- to a long-range scale. The latter involves a distance of approximately 2000 m. The developed AR system enables users to simulate a Landscape from multiple and longdistance viewpoints simultaneously and to walk around the viewpoint fields using only a smartphone. This result is the tolerance level of Landscape assessment. In conclusion, the proposed method is evaluated as feasible and effective.

A Modified CycleGAN for Multi-Organ Ultrasound Image Enhancement via Unpaired Pre-Training

Handheld ultrasound devices are known for their portability and affordability,making them widely utilized in underdeveloped areas and community healthcare for rapid diagnosis and early screening.However,the image quality of handheld ultrasound devices is not always satisfactory due to the limited equipment size,which hinders accurate diagnoses by doctors.At the same time,paired ultrasound images are difficult to obtain from the clinic because imaging process is complicated.Therefore,we propose a modified cycle generative adversarial network(cycleGAN) for ultrasound image enhancement from multiple organs via unpaired pre-training.We introduce an ultrasound image pre-training method that does not require paired images,alleviating the requirement for large-scale paired datasets.We also propose an enhanced block with different structures in the pre-training and fine-tuning phases,which can help achieve the goals of different training phases.To improve the robustness of the model,we add Gaussian noise to the training images as data augmentation.Our approach is effective in obtaining the best quantitative evaluation results using a small number of parameters and less training costs to improve the quality of handheld ultrasound devices.