• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권6호
• /
• pp.2044-2059
• /
• 2022

Recent works have shown that the geometric constraint can be harnessed to boost the performance of CNN-based camera localization. However, the existing strategies are limited to imposing image-level constraint between pose pairs, which is weak and coarse-gained. In this paper, we introduce a pixel-level epipolar geometry constraint to vanilla localization framework without the ground-truth 3D information. Dubbed EpiLoc, our method establishes the geometric relationship between pixels in different images by utilizing the epipolar geometry thus forcing the network to regress more accurate poses. We also propose a variant called EpiSingle to cope with non-sequential training images, which can construct the epipolar geometry constraint based on a single image in a self-supervised manner. Extensive experiments on the public indoor 7Scenes and outdoor RobotCar datasets show that the proposed pixel-level constraint is valuable, and helps our EpiLoc achieve state-of-the-art results in the end-to-end camera localization task.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권8호
• /
• pp.3312-3327
• /
• 2020

Plant diseases are a significant yield and quality constraint for farmers around the world due to their severe impact on agricultural productivity. Such losses can have a substantial impact on the economy which causes a reduction in farmer's income and higher prices for consumers. Further, it may also result in a severe shortage of food ensuing violent hunger and starvation, especially, in less-developed countries where access to disease prevention methods is limited. This research presents an investigation of Directional Local Quinary Patterns (DLQP) as a feature descriptor for plants leaf disease detection and Support Vector Machine (SVM) as a classifier. The DLQP as a feature descriptor is specifically the first time being used for disease detection in horticulture. DLQP provides directional edge information attending the reference pixel with its neighboring pixel value by involving computation of their grey-level difference based on quinary value (-2, -1, 0, 1, 2) in 0°, 45°, 90°, and 135° directions of selected window of plant leaf image. To assess the robustness of DLQP as a texture descriptor we used a research-oriented Plant Village dataset of Tomato plant (3,900 leaf images) comprising of 6 diseased classes, Potato plant (1,526 leaf images) and Apple plant (2,600 leaf images) comprising of 3 diseased classes. The accuracies of 95.6%, 96.2% and 97.8% for the above-mentioned crops, respectively, were achieved which are higher in comparison with classification on the same dataset using other standard feature descriptors like Local Binary Pattern (LBP) and Local Ternary Patterns (LTP). Further, the effectiveness of the proposed method is proven by comparing it with existing algorithms for plant disease phenotyping.

• 한국의학물리학회지:의학물리
• /
• 제13권1호
• /
• pp.32-36
• /
• 2002

세기조절방사선치료(Intensity Modulated Radiation TheraIntensity modulated radiation therapy ; Virtual micro-IMRT ; Intensity map ; MLCpy)에서 세기분포도(intensity map; IM)의 공간적 분해능은 방사선 민감장기(Critical Organ)를 보호하면서 종양에 최대 선량을 주는데 매우 중요하며, 일반적으로 다엽콜리메이터(MLC)의 폭에 좌우된다. 세기분포도의 공간적 분해능을 향상시키기 위한 방법으로는 두. 가지 방법이 있는데, 하드웨어를 추가하는 방법과 방사선 조사 기술을 변경하는 것이다. 물론 다엽콜리메이터의 폭을 작게 만드는 것이 최상의 방법이나, 하드웨어 기술적으로 어렵고 또한 추가비용이 많이 들게 된다. 따라서 여기에서는 추가적 비용이 들지 않으면서 기존의 장비를 그대로 활용할 수 있는 기술적 방법 중의 하나인 가상 미세 세기조절방사선치료(Virtual micro-IMRT) 기법을 구현하여 임상적으로 적용을 하기 위한 예비적 연구를 수행하였다. 가상의 42$\times$54 픽셀크기, 0.5cm의 15 level IM을 이용하여 1$\times$1cm, 0.5$\times$lcm, 0.5$\times$0.5cm(VMIM) beamlet 크기에 대해 비교하였다. 분석결과, 기대와는 달리, 1cm 폭의 MLC로 전달가능한 0.5$\times$lcm beamlet에 비해 크게 개선되지 않았다. 이는 VMIM의 제약조건에 기인되는 것으로 판단된다. 향후, 두경부암에서와 같이 1cm이하의 beamlet 분해능이 요구되는 경우에 적용시켜 추가적인 연구가 필요하다 하겠다.