Plant phenotyping focuses on the measurement of plant characteristics throughout the growing season, typically with the goal of evaluating genotypes for plant breeding. Estimating plant location is important for identifying genotypes which have low emergence, which is also related to the environment and management practices such as fertilizer applications. The goal of this paper is to investigate methods that estimate plant locations for a field-based crop using RGB aerial images captured using Unmanned Aerial Vehicles (UAVs). Deep learning approaches provide promising capability for locating plants observed in RGB images, but they require large quantities of labeled data (ground truth) for training. Using a deep learning architecture fine-tuned on a single field or a single type of crop on fields in other geographic areas or with other crops may not have good results. The problem of generating ground truth for each new field is labor-intensive and tedious. In this paper, we propose a method for estimating plant centers by transferring an existing model to a new scenario using limited ground truth data. We describe the use of transfer learning using a model fine-tuned for a single field or a single type of plant on a varied set of similar crops and fields. We show that transfer learning provides promising results for detecting plant locations.
Agricultural robots are expected to increase yields in a sustainable way and automate precision tasks, such as weeding and plant monitoring. At the same time, they move in a continuously changing, semi-structured field environment, in which features can hardly be found and reproduced at a later time. Challenges for Lidar and visual detection systems stem from the fact that plants can be very small, overlapping and have a steadily changing appearance. Therefore, a popular way to localize vehicles with high accuracy is based on ex- pensive global navigation satellite systems and not on natural l…
Universitas Multimedia Nusantara（印尼多媒体大学）；Tilburg University（蒂尔堡大学）
We propose an improved eye center localization method based on the Hough transform, called Circle-based Eye Center Localization (CECL) that is simple, robust, and achieves accuracy on a par with typically more complex state-of-the-art methods. The CECL method relies on color and shape cues that distinguish the iris from other facial structures. The accuracy of the CECL method is demonstrated through a comparison with 15 state-of-the-art eye center localization methods against five error thresholds, as reported in the literature. The CECL method achieved an accuracy of 80.8% to 99.4% and ranked…
This paper proposes a new framework for the eye centers localization by the joint use of encoding of normalized image projections and a Multi Layer Perceptron (MLP) classifier. The encoding is novel and it consists in identifying the zero-crossings and extracting the relevant parameters from the resulting modes. The compressed normalized projections produce feature descriptors that are inputs to a properly-trained MLP, for discriminating among various categories of image regions. The proposed framework forms a fast and reliable system for the eye centers localization, especially in the context…
ModiFace Inc.（ModiFace公司）；University of Toronto（多伦多大学）
We propose a new cascaded regressor for eye center detection. Previous methods start from a face or an eye detector and use either advanced features or powerful regressors for eye center localization, but not both. Instead, we detect the eyes more accurately using an existing facial feature alignment method. We improve the robustness of localization by using both advanced features and powerful regression machinery. Unlike most other methods that do not refine the regression results, we make the localization more accurate by adding a robust circle fitting post-processing step. Finally, using a …
Inception Institute of Artificial Intelligence（Inception人工智能研究院）
Temporal action localization is a challenging computer vision problem with numerous real-world applications. Most existing methods require laborious frame-level supervision to train action localization models. In this work, we propose a framework, called 3C-Net, which only requires video-level supervision (weak supervision) in the form of action category labels and the corresponding count. We introduce a novel formulation to learn discriminative action features with enhanced localization capabilities. Our joint formulation has three terms: a classification term to ensure the separability of le…
Shantou University（汕头大学）；College of Engineering（工学院）
Automated steel bar counting and center localization plays an important role in the factory automation of steel bars. Traditional methods only focus on steel bar counting and their performances are often limited by complex industrial environments. Convolutional neural network (CNN), which has great capability to deal with complex tasks in challenging environments, is applied in this work. A framework called CNN-DC is proposed to achieve automated steel bar counting and center localization simultaneously. The proposed framework CNN-DC first detects the candidate center points with a deep CNN. T…
National Institute of Technology, Rourkela（鲁尔凯拉国家理工学院）
Vision-based pose estimation of Unmanned Aerial Vehicles (UAV) in unknown environments is a rapidly growing research area in the field of robot vision. The task becomes more complex when the only available sensor is a static single camera (monocular vision). In this regard, we propose a monocular vision assisted localization algorithm, that will help a UAV to navigate safely in indoor corridor environments. Always, the aim is to navigate the UAV through a corridor in the forward direction by keeping it at the center with no orientation either to the left or right side. The algorithm makes use …
Rethinking Plant Disease Diagnosis: Bridging the Academic-Practical Gap with Vision Transformers and Zero-Shot Learning
Department of Computer Science, Mohamed El Bachir El Ibrahimi University（计算机科学系，莫亨德·埃巴希里·埃布拉希米大学）；Laboratory of Physical Chemistry and Biological Materials（物理化学与生物材料实验室）；Laboratory of Informatics and its Applications of M’sila, Mohamed Boudiaf University（信息学及其应用实验室，莫赫梅德·布迪亚夫大学）；Department of Computer Science, Mohamed Boudiaf University（计算机科学系，莫赫梅德·布迪亚夫大学）；Department of agricultural science, Mohamed El Bachir El Ibrahimi University（农业科学系，莫亨德·埃巴希里·埃布拉希米大学）；Laboratoire d’Amélioration et de Développement de la Production Végétale et Animale (LADPVA), University of Ferhat ABBAS (UFAS-Sétif1)（植物和动物生产改良与发展实验室（LADPVA），费哈特·阿巴斯大学（UFAS-Sétif1））
Indian Institute of Technology Bombay（印度理工学院孟买分校）；Indian Institute of Science（印度科学学院）；National Institute of Technology, Tiruchirappalli（印度国立理工学院蒂鲁吉拉伯利分校）
Diabetic Retinopathy is the leading cause of blindness in the world. At least 90\% of new cases can be reduced with proper treatment and monitoring of the eyes. However, scanning the entire population of patients is a difficult endeavor. Computer-aided diagnosis tools in retinal image analysis can make the process scalable and efficient. In this work, we focus on the problem of localizing the centers of the Optic disc and Fovea, a task crucial to the analysis of retinal scans. Current systems recognize the Optic disc and Fovea individually, without exploiting their relations during learning. W…
Deep Learning-Based Breast Cancer Detection in Mammography: A Multi-Center Validation Study in Thai Population
Perceptra Co., Ltd（Perceptra公司）；Institute of Field Robotics（现场机器人研究所）；King Mongkut’s University of Technology Thonburi（技术师范大学）；Mahidol University（玛希多大学）；Siriraj Hospital（Siriraj医院）；Khonkaen University（孔卡恩大学）
