Unsupervised online learning of condition-invariant images for place recognition

This paper presents an online, unsupervised training algorithm enabling vision-based place recognition across a wide range of changing environmental conditions such as those caused by weather, seasons, and day-night cycles. The technique applies principal component analysis to distinguish between aspects of a location’s appearance that are condition-dependent and those that are condition-invariant. Removing the dimensions associated with environmental conditions produces condition-invariant images that can be used by appearance-based place recognition methods. This approach has a unique benefit – it requires training images from only one type of environmental condition, unlike existing data-driven methods that require training images with labelled frame correspondences from two or more environmental conditions. The method is applied to two benchmark variable condition datasets. Performance is equivalent or superior to the current state of the art despite the lesser training requirements, and is demonstrated to generalise to previously unseen locations.

A shallow water AUV for benthic and water column observations

Autonomous underwater vehicles (AUVs) are becoming commonplace in the study of inshore coastal marine habitats. Combined with shipboard systems, scientists are able to make in-situ measurements of water column and benthic properties. In CSIRO, autonomous gliders are used to collect water column data, while surface vessels are used to collect bathymetry information through the use of swath mapping, bottom grabs, and towed video systems. Although these methods have provided good data coverage for coastal and deep waters beyond 50m, there has been an increasing need for autonomous in-situ sampling in waters less than 50m deep. In addition, the collection of benthic and water column data has been conducted separately, requiring extensive post-processing to combine data streams. As such, a new AUV was developed for in-situ observations of both benthic habitat and water column properties in shallow waters. This paper provides an overview of the Starbug X AUV system, its operational characteristics including vision-based navigation and oceanographic sensor integration.

Segmentation and recognition using structure from motion point clouds

We propose an algorithm for semantic segmentation based on 3D point clouds derived from ego-motion. We motivate five simple cues designed to model specific patterns of motion and 3D world structure that vary with object category. We introduce features that project the 3D cues back to the 2D image plane while modeling spatial layout and context. A randomized decision forest combines many such features to achieve a coherent 2D segmentation and recognize the object categories present. Our main contribution is to show how semantic segmentation is possible based solely on motion-derived 3D world structure. Our method works well on sparse, noisy point clouds, and unlike existing approaches, does not need appearance-based descriptors. Experiments were performed on a challenging new video database containing sequences filmed from a moving car in daylight and at dusk. The results confirm that indeed, accurate segmentation and recognition are possible using only motion and 3D world structure. Further, we show that the motion-derived information complements an existing state-of-the-art appearance-based method, improving both qualitative and quantitative performance. © 2008 Springer Berlin Heidelberg.

Video segmentation with superpixels

Due to its importance, video segmentation has regained interest recently. However, there is no common agreement about the necessary ingredients for best performance. This work contributes a thorough analysis of various within- and between-frame affinities suitable for video segmentation. Our results show that a frame-based superpixel segmentation combined with a few motion and appearance-based affinities are sufficient to obtain good video segmentation performance. A second contribution of the paper is the extension of [1] to include motion-cues, which makes the algorithm globally aware of motion, thus improving its performance for video sequences. Finally, we contribute an extension of an established image segmentation benchmark [1] to videos, allowing coarse-to-fine video segmentations and multiple human annotations. Our results are tested on BMDS [2], and compared to existing methods. © 2013 Springer-Verlag.

基于GPS的蛇形机器人导航方法

将GPS技术应用于蛇形机器人自主运动控制.根据蛇形机器人的基本运动方式, 针对其现有的前进、后退、近似角度转弯等运动特点,提出了一种适用于该种蛇形机器人的自主移动算法,即用蛇头运动的方向近似看作蛇体运动方向.通过仿真验证了该算法的有效性,能够使蛇形机器人自主地到达目标点。

基于DM642的香烟小包装外观检测系统

本文设计与实现了一种基于TMS320DM642的香烟小包装外观质量检测系统,详细阐述了该系统的硬件构成、软件流程、检测算法以及针对DSP处理器进行的系统优化。系统以TMS320DM642处理器为核心建立硬件平台,通过摄像头获取香烟小包装图像,采用改进的模板匹配算法对当前图像进行质量检测,最终在监视器上显示检测结果并将检测结果送执行单元进行处理。实验结果表明基于TMS320DM642的香烟小包装检测系统,检测效果快速、准确、有效,应用前景广泛。

视频图像处理在小包外观检测中的应用研究

香烟小包装在线实时检测系统是一种烟草行业产品包装检测设备,具有广阔的应用前景。在现代生产过程中，生产速度越来越快，对产品质量的要求也越来越高。烟草企业在香烟的生产过程中，从烟叶制丝到卷、接、包装都已经实现了自动化。香烟小包装的外观质量，反映了烟厂的技术装备水平，涉及到企业的形象、信誉问题，同时，有质量缺陷的香烟小包装被市场反馈回企业，也会带来企业成本的增加。 随着计算机软件、硬件技术的发展，以及机器视觉理论的完善，采用机器视觉的方法来检测香烟小包装的外观质量，已经开始应用。机器视觉在检测方面具有先天优势检测速度快、分辨能力高、规范化程度高、可重复性好。采用现代机器视觉技术来进行香烟小包装外观质量的检测，可以大大降低检验人员的劳动强度，提高产品的质量，减少烟厂的人力成本和管理成本，改善企业形象。 本文分析了国内外烟包包装质量检测的许多方法，设计了一套基于DSP的香烟小包装外观质量检测系统，可以对香烟小包装进行实时检测，达到实时剔除有包装质量缺陷的香烟小包装的目的。 从机器视觉的角度出发，本文阐述了视觉检测系统的工作原理、总体机构及系统的工作流程，同时对比各种硬件特性，进行了光源、传感器、相机、镜头及DSP芯片的选型，着重介绍了图像处理算法，尤其是本系统中用到的图像配准、模板匹配以及各种缺陷的识别进行了详细的描述，并给出了程序在DSP中的优化方法。 本文对设计的系统进行了一系列的实验和测试，结果表明，本系统具有速度快，总体检测效果好，稳定性好的特点，可以达到香烟小包装实时检测的要求。

Testing the role of sensory systems in the migratory heading of a songbird

The identification of the sensory cues and mechanisms by which migratory birds are able to reach the same breeding and wintering grounds year after year has eluded biologists despite more than 50 years of intensive study. While a number of environmental cues have been proposed to play a role in the navigation of birds, arguments still persist about which cues are essential for the experience based navigation shown by adult migrants. To date, few studies have tested the sensory basis of navigational cues used during actual migration in the wild: mainly laboratory based studies or homing during the non-migratory season have been used to investigate this behaviour. Here we tested the role of olfactory and magnetic cues in the migration of the catbird (Dumetella carolinensis) by radio tracking the migration of birds with sensory manipulations during their actual migratory flights. Our data suggest that adult birds treated with zinc sulphate to produce anosmia were unable to show the same orientation as control adults, and instead reverted to a direction similar to that shown by juveniles making their first migration. The magnetic manipulation had no effect on the orientation of either adults or juveniles. These results allow us to propose that the olfactory sense may play a role in experience based migration in adult catbirds. While the olfactory sense has been shown to play a role in the homing of pigeons and other birds, this is the first time it has been implicated in migratory orientation.

Contribuições para a localização e mapeamento em robótica através da identificação visual de lugares

Tese de doutoramento, Informática (Engenharia Informática), Universidade de Lisboa, Faculdade de Ciências, 2015

The influence of physical attractiveness and gender on perceived competence of sportscasters

The media tends to represent female athletes as women first and athletes second (Koivula, 1 999). The present study investigated whether this same trend was present for female sportscasters, using a self-presentational framework. Self-presentation is the process by which people try to control how others see them (Leary, 1995). One factor that may influence the type of image they try to project is their roles held in society, including gender roles. The gender roles for a man include dominance, assertiveness, and masculinity, while the gender roles for a woman include nurturer, femininity, and attractiveness (Deaux & Major, 1 987). By contrast, sports broadcasters are expected to be knowledgeable, assertive, and competent. Research suggests that female sports broadcasters are seen as less competent and less persuasive than male sports broadcasters (Mitrook & Dorr, 2001; Ordman & Zillmann, 1994, Toro, 2005). One reason for this difference may be that the gender roles for a man are much more similar to those of a sportscaster, compared to those of a woman. Thus, there may be a conflict between the two roles for women. The present study investigated whether the gender and perceived attractiveness of sportscasters influenced the audience's perceptions of the level of competence that a sportscaster demonstrates. Two hundred and four male (n =75) and female (n =129) undergraduate students were recruited from a southern Ontario university to participate in the study. The average age of the male participants was 21 .23 years {SD =1 .60), and the average age for female participants was 20.67 years {SD = 1 .31). The age range for all participants was from 19 to 30 years {M = 20.87 years, SD = 1 .45). Af^er providing informed consent, participants randomly received one of four possible questionnaire packages. The participants answered the demographic questionnaire, and then proceeded to view the picture and read the script of a sports newscast. Next, based on the picture and script, the participants answered the competence questionnaire, assessing the general, sport specific, and overall competence of the sportscaster. Once participants had finished, they returned the package to the researcher and were thanked for their time. Data was analyzed using an ANOVA to determine if general sport competence differs with respect to gender and attractiveness of the sportscaster. Overall, the ANOVA was non-significant (p > .05), indicating no differences on the dependent variable based on gender (F (3, 194) = .631, p = .426), attractiveness (F (3, 194) = .070, p = .791), or the interaction of the two {F (3, 194) = .043,/? = .836). Although none of the study hypotheses were supported, the study provided some insight to the perceived competence of female sportscasters. It is possible that female sportscasters are now seen as competent in the area of sports. Sample characteristics could also have influenced these results; the participants in the current study were primarily physical education and kinesiology students, who had experience participating in physical activity with both men and women. Future research should investigate this issue further by using a video sportscast. It is possible that delivery characteristics such as voice quality or eye contact may also impact perceptions of sportscasters.

Video Object Tracking And Analysis For Computer Assisted Surgery

Pedicle screw insertion technique has made revolution in the surgical treatment of spinal fractures and spinal disorders. Although X- ray fluoroscopy based navigation is popular, there is risk of prolonged exposure to X- ray radiation. Systems that have lower radiation risk are generally quite expensive. The position and orientation of the drill is clinically very important in pedicle screw fixation. In this paper, the position and orientation of the marker on the drill is determined using pattern recognition based methods, using geometric features, obtained from the input video sequence taken from CCD camera. A search is then performed on the video frames after preprocessing, to obtain the exact position and orientation of the drill. An animated graphics, showing the instantaneous position and orientation of the drill is then overlaid on the processed video for real time drill control and navigation

Probabilistic sonar scan matching for an AUV

This paper proposes MSISpIC, a probabilistic sonar scan matching algorithm for the localization of an autonomous underwater vehicle (AUV). The technique uses range scans gathered with a Mechanical Scanning Imaging Sonar (MSIS), the robot displacement estimated through dead-reckoning using a Doppler velocity log (DVL) and a motion reference unit (MRU). The proposed method is an extension of the pIC algorithm. An extended Kalman filter (EKF) is used to estimate the robot-path during the scan in order to reference all the range and bearing measurements as well as their uncertainty to a scan fixed frame before registering. The major contribution consists of experimentally proving that probabilistic sonar scan matching techniques have the potential to improve the DVL-based navigation. The algorithm has been tested on an AUV guided along a 600 m path within an abandoned marina underwater environment with satisfactory results

Learning enhanced 3D models for vehicle tracking

This paper presents an enhanced hypothesis verification strategy for 3D object recognition. A new learning methodology is presented which integrates the traditional dichotomic object-centred and appearance-based representations in computer vision giving improved hypothesis verification under iconic matching. The "appearance" of a 3D object is learnt using an eigenspace representation obtained as it is tracked through a scene. The feature representation implicitly models the background and the objects observed enabling the segmentation of the objects from the background. The method is shown to enhance model-based tracking, particularly in the presence of clutter and occlusion, and to provide a basis for identification. The unified approach is discussed in the context of the traffic surveillance domain. The approach is demonstrated on real-world image sequences and compared to previous (edge-based) iconic evaluation techniques.

Sistema de supervisão aérea baseado em navegação visual para detecção de anomalias em instalações de petróleo e gás

This work deals with the development of a prototype of a helicopter quadrotor for monitoring applications in oil facilities. Anomaly detection problems can be resolved through monitoringmissions performed by a suitably instrumented quadrotor, i.e. infrared thermosensors should be embedded. The proposed monitoring system aims to reduce accidents as well as to make possible the use of non-destructive techniques for detection and location of leaks caused by corrosion. To this end, the implementation of a prototype, its stabilization and a navigation strategy have been proposed. The control strategy is based on dividing the problem into two control hierarchical levels: the lower level stabilizes the angles and the altitude of the vehicle at the desired values, while the higher one provide appropriate references signals to the lower level in order the quadrotor performs the desired movements. The navigation strategy for helicopter quadrotor is made using information provided by a acquisition image system (monocular camera) embedded onto the helicopter. Considering that the low-level control has been solved, the proposed vision-based navigation technique treats the problem as high level control strategies, such as, relative position control, trajectory generation and trajectory tracking. For the position control we use a control technique for visual servoing based on image features. The trajectory generation is done in a offline step, which is a visual trajectory composed of a sequence of images. For the trajectory tracking problem is proposed a control strategy by continuous servovision, thus enabling a navigation strategy without metric maps. Simulation and experimental results are presented to validate the proposal

Infrared face recogniton by optimum-path forest

This paper presents a novel, fast and accurate appearance-based method for infrared face recognition. By introducing the Optimum-Path Forest classifier, our objective is to get good recognition rates and effectively reduce the computational effort. The feature extraction procedure is carried out by PCA, and the results are compared to two other well known supervised learning classifiers; Artificial Neural Networks and Support Vector Machines. The achieved performance asserts the promise of the proposed framework. ©2009 IEEE.