Quality evaluation of agricultural and food products is important for processing, inventory control, and marketing. Fruit size and surface quality are two important quality factors for high-quality fruit such as Medjo...
详细信息
ISBN:
(纸本)9780819499424
Quality evaluation of agricultural and food products is important for processing, inventory control, and marketing. Fruit size and surface quality are two important quality factors for high-quality fruit such as Medjool dates. Fruit size is usually measured by length that can be done easily by simple image processing techniques. Surface quality evaluation on the other hand requires more complicated design, both in image acquisition and image processing. Skin delamination is considered a major factor that affects fruit quality and its value. This paper presents an efficient histogram analysis and image processing technique that is designed specifically for real-time surface quality evaluation of Medjool dates. This approach, based on short-wave infrared imaging, provides excellent image contrast between the fruit surface and delaminated skin, which allows significant simplification of image processing algorithm and reduction of computational power requirements. The proposed quality grading method requires very simple training procedure to obtain a gray scale image histogram for each quality level. Using histogram comparison, each date is assigned to one of the four quality levels and an optimal threshold is calculated for segmenting skin delamination areas from the fruit surface. The percentage of the fruit surface that has skin delamination can then be calculated for quality evaluation. This method has been implemented and used for commercial production and proven to be efficient and accurate.
This paper aims to address a trace- guided real-time navigation and map building approach of an autonomous mobile robot. Wave-front based global path planner is developed to generate a global trajectory for an autonom...
详细信息
ISBN:
(纸本)9780819499424
This paper aims to address a trace- guided real-time navigation and map building approach of an autonomous mobile robot. Wave-front based global path planner is developed to generate a global trajectory for an autonomous mobile robot. Modified Vector Field Histogram (M-VFH) is employed based on the LIDAR sensor information to guide the robot locally to be autonomously traversed with obstacle avoidance by following traces provided by the global path planner. A local map composed of square grids is created through the local navigator while the robot traverses with limited LIDAR sensory information. From the measured sensory information, a map of the robot's immediate limited surroundings is dynamically built for the robot navigation. The real-time wave-front based navigation and map building methodology has been successfully demonstrated in a Player/Stage simulation environment. With the wave-front-based global path planner and M-VFH local navigator, a safe, short, and reasonable trajectory is successfully planned in a majority of situations without any templates, without explicitly optimizing any global cost functions, and without any learning procedures. Its effectiveness, feasibility, efficiency and simplicity of the proposed real-time navigation and map building of an autonomous mobile robot have been successfully validated by simulation and comparison studies. Comparison studies of the proposed approach with the other path planning approaches demonstrate that the proposed method is capable of planning more reasonable and shorter collision-free trajectories autonomously.
Many large-scale systems benefit from an organizational structure to provide for problem decomposition. A pivotal problem solving setting is given by hierarchical control systems familiar from hierarchical task networ...
详细信息
Many large-scale systems benefit from an organizational structure to provide for problem decomposition. A pivotal problem solving setting is given by hierarchical control systems familiar from hierarchical task networks. If these structures can be modified autonomously by, e.g., Coalition formation and reconfiguration, adequate decisions on higher levels require a faithful abstracted model of a collective of agents. An illustrative example is found in calculating schedules for a set of power plants organized in a hierarchy of Autonomous Virtual Power Plants. Functional dependencies over the combinatorial domain, such as the joint costs or rates of change of power production, are approximated by repeatedly sampling input-output pairs and substituting the actual functions by piecewise linear functions. However, if the sampled data points are weakly informative, the resulting abstracted high-level optimization introduces severe errors. Furthermore, obtaining additional point labels amounts to solving computationally hard optimization problems. Building on prior work, we propose to apply techniques from active learning to maximize the information gained by each additional point. Our results show that significantly better allocations in terms of cost-efficiency (up to 33.7 % reduction in costs in our case study) can be found with fewer but carefully selected sampling points using Decision Forests.
In this study, we designed an autonomous mobile robot according to the rules of the Federation of International Robot-soccer Association (FIRA) RoboSot category, integrating the techniques of computervision, real-tim...
详细信息
In this study, we designed an autonomous mobile robot according to the rules of the Federation of International Robot-soccer Association (FIRA) RoboSot category, integrating the techniques of computervision, real-time image processing, dynamic target tracking, wireless communication, self-localization, motion control, path planning, and control strategy to achieve the contest goal. The real time self-localization scheme of the mobile robot is based on the algorithms extracting white lines from the soccer field featured in the images from the omni-vision system. The proposed algorithm uses the white line distances from 360 degree direction between the robot and the rotation angle of the robot obtained from the gyroscope as a featured vector. The feature vector is compared with the pre-built in patterns of the database. The location of the robot is obtained from the location of the matched pattern with the minimum error of the featured vector. The results demonstrate that the proposed algorithm is accurate, exhibiting a 10 cm (distance) and 1 degree (rotation) position error in a soccer field measuring 750 cm × 550 cm within processing time about 5 milliseconds. The real time self-localization system can be practically implemented in 2014 FIRA Robot Soccer Competition to fulfill the contest requirement.
In this paper, we present an intelligent facial emotion recognition system with real-time face tracking for a humanoid robot. The system is able to detect facial actions and emotions from images with up to 60 degrees ...
详细信息
ISBN:
(纸本)9781634391313
In this paper, we present an intelligent facial emotion recognition system with real-time face tracking for a humanoid robot. The system is able to detect facial actions and emotions from images with up to 60 degrees of pose variations. We employ the active Appearance Model to perform real-time face tracking and extract both texture and geometric representations of images. A POSIT algorithm is also used to identify head rotations. The extracted texture and shape features are employed to detect 18 facial actions and seven basic emotions. The overall system is integrated with a humanoid robot platform to further extend its vision APIs. The system proved to be able to deal with challenging facial emotion recognition tasks with various pose variations.
The regularity of everyday tasks enables us to reuse existing solutions for task variations. For instance, most door-handles require the same basic skill (reach, grasp, turn, pull), but small adaptations of the basic ...
详细信息
ISBN:
(纸本)9781479969357
The regularity of everyday tasks enables us to reuse existing solutions for task variations. For instance, most door-handles require the same basic skill (reach, grasp, turn, pull), but small adaptations of the basic skill are required to adapt to the variations that exist (e.g. levers vs. knobs). We introduce the algorithm "Simultaneous On-line Discovery and Improvement of Robotic Skills" (SODIRS) that is able to autonomously discover and optimize skill options for such task variations. We formalize the problem in a reinforcement learning context, and use the PI~(BB) algorithm [2] to continually optimize skills with respect to a cost function. SODIRS discovers new subskills, or "skill options", by clustering the costs of trials, and determining whether perceptual features are able to predict which cluster a trial will belong to. This enables SODIRS to build a decision tree, in which the leaves contain skill options for task variations. We demonstrate SODIRS' performance in simulation, as well as on a Meka humanoid robot performing the ball-in-cup task.
With the development of the application of visual tracking technology, the performance of visual tracking algorithm is important. Due to many kinds of voice, robust of tracking algorithm is bad. To improve identificat...
详细信息
ISBN:
(纸本)9780819494351
With the development of the application of visual tracking technology, the performance of visual tracking algorithm is important. Due to many kinds of voice, robust of tracking algorithm is bad. To improve identification rate and track rate for quickly moving target, expand tracking scope and lower sensitivity to illumination varying, an active visual tracking system based on illumination invariants is proposed. Camera motion pre-control method based on particle filter pre-location is used to improve activity and accuracy of track for quickly moving target by forecasting target position and control camera joints of Tilt, Pan and zoom. Pre-location method using particle sample filter according to illumination invariants of target is used to reduce the affect of varying illumination during tracking moving target and to improve algorithm robust. Experiments in intelligent space show that the robust to illumination vary is improved and the accuracy is improved by actively adjust PTZ parameters.
In this paper, we identify some of the existing problems in shape context matching. We first identify the need for reflection invariance in shape context matching algorithms and propose a method to achieve the same. W...
详细信息
ISBN:
(纸本)9780819494351
In this paper, we identify some of the existing problems in shape context matching. We first identify the need for reflection invariance in shape context matching algorithms and propose a method to achieve the same. With the use of these reflection invariance techniques, we bring all the objects, in a database, to their canonical form, which halves the time required to match two shapes using their contexts. We then show how we can build better shape descriptors by the use of geodesic information from the shapes and hence improve upon the well-known Inner Distance Shape Context (IDSC). The IDSC is used by many pre- and post-processing algorithms as the baseline shape-matching algorithm. Our improvements to IDSC will remain compatible for use with those algorithms. Finally, we introduce new comparison metrics that can be used for the comparison of two or more algorithms. We have tested our proposals on the MPEG-7 database and show that our methods significantly outperform the IDSC.
This paper presents the Mobile Intelligence Team's approach to addressing the CANINE outdoor ground robot competition. The competition required developing a robot that provided retrieving capabilities similar to a...
详细信息
ISBN:
(纸本)9780819494351
This paper presents the Mobile Intelligence Team's approach to addressing the CANINE outdoor ground robot competition. The competition required developing a robot that provided retrieving capabilities similar to a dog, while operating fully autonomously in unstructured environments. The vision team consisted of Mobile Intelligence, the Georgia Institute of Technology, and Wayne State University. Important computervision aspects of the project were the ability to quickly learn the distinguishing characteristics of novel objects, searching images for the object as the robot drove a search pattern, identifying people near the robot for safe operations, correctly identify the object among distractors, and localizing the object for retrieval. The classifier used to identify the objects will be discussed, including an analysis of its performance, and an overview of the entire system architecture presented. A discussion of the robot's performance in the competition will demonstrate the system's successes in real-world testing.
This paper introduces a novel image description technique that aims at appearance based loop closure detection for mobile robotics applications. This technique relies on the local evaluation of the Zernike Moments. Bi...
详细信息
ISBN:
(纸本)9780819494351
This paper introduces a novel image description technique that aims at appearance based loop closure detection for mobile robotics applications. This technique relies on the local evaluation of the Zernike Moments. Binary patterns, which are referred to as Local Zernike Moment (LZM) patterns, are extracted from images, and these binary patterns are coded using histograms. Each image is represented with a set of histograms, and loop closure is achieved by simply comparing the most recent image with the images in the past trajectory. The technique has been tested on the New College dataset, and as far as we know, it outperforms the other methods in terms of computation efficiency and loop closure precision.
暂无评论