An active vision system integrating fast and slow processes

[EN]This paper describes an Active Vision System whose design assumes a distinction between fast or reactive and slow or background processes. Fast processes need to operate in cycles with critical timeouts that may affect system stability. While slow processes, though necessary, do not compromise system stability if its execution is delayed. Based on this simple taxonomy, a control architecture has been proposed and a prototype implemented that is able to track people in real-time with a robotic head while trying to identify the target. In this system, the tracking module is considered as the reactive part of the system while person identification is considered a background task.

A C80 DSP-based active vision system for real-time tracking

[EN]Active Vision Systems can be considered as dynamical systems which close the loop around artificial visual perception, controlling camera parameters, motion and also controlling processing to simplify, accelerate and do more robust visual perception. Research and Development in Active Vision Systems [Aloi87], [Bajc88] is a main area of interest in Computer Vision, mainly by its potential application in different scenarios where real-time performance is needed such as robot navigation, surveillance, visual inspection, among many others. Several systems have been developed during last years using robotic-heads for this purpose...

Design and Pilot Study for an Efficient High-Throughput Automated Computer-Vision Guided Intelligent De-Calyxing Machine for Post-Harvest Strawberry Processing

Strawberries harvested for processing as frozen fruits are currently de-calyxed manually in the field. This process requires the removal of the stem cap with green leaves (i.e. the calyx) and incurs many disadvantages when performed by hand. Not only does it necessitate the need to maintain cutting tool sanitation, but it also increases labor time and exposure of the de-capped strawberries before in-plant processing. This leads to labor inefficiency and decreased harvest yield. By moving the calyx removal process from the fields to the processing plants, this new practice would reduce field labor and improve management and logistics, while increasing annual yield. As labor prices continue to increase, the strawberry industry has shown great interest in the development and implementation of an automated calyx removal system. In response, this dissertation describes the design, operation, and performance of a full-scale automatic vision-guided intelligent de-calyxing (AVID) prototype machine. The AVID machine utilizes commercially available equipment to produce a relatively low cost automated de-calyxing system that can be retrofitted into existing food processing facilities. This dissertation is broken up into five sections. The first two sections include a machine overview and a 12-week processing plant pilot study. Results of the pilot study indicate the AVID machine is able to de-calyx grade-1-with-cap conical strawberries at roughly 66 percent output weight yield at a throughput of 10,000 pounds per hour. The remaining three sections describe in detail the three main components of the machine: a strawberry loading and orientation conveyor, a machine vision system for calyx identification, and a synchronized multi-waterjet knife calyx removal system. In short, the loading system utilizes rotational energy to orient conical strawberries. The machine vision system determines cut locations through RGB real-time feature extraction. The high-speed multi-waterjet knife system uses direct drive actuation to locate 30,000 psi cutting streams to precise coordinates for calyx removal. Based on the observations and studies performed within this dissertation, the AVID machine is seen to be a viable option for automated high-throughput strawberry calyx removal. A summary of future tasks and further improvements is discussed at the end.

Continual learning for computer vision applications

One of the most visionary goals of Artificial Intelligence is to create a system able to mimic and eventually surpass the intelligence observed in biological systems including, ambitiously, the one observed in humans. The main distinctive strength of humans is their ability to build a deep understanding of the world by learning continuously and drawing from their experiences. This ability, which is found in various degrees in all intelligent biological beings, allows them to adapt and properly react to changes by incrementally expanding and refining their knowledge. Arguably, achieving this ability is one of the main goals of Artificial Intelligence and a cornerstone towards the creation of intelligent artificial agents. Modern Deep Learning approaches allowed researchers and industries to achieve great advancements towards the resolution of many long-standing problems in areas like Computer Vision and Natural Language Processing. However, while this current age of renewed interest in AI allowed for the creation of extremely useful applications, a concerningly limited effort is being directed towards the design of systems able to learn continuously. The biggest problem that hinders an AI system from learning incrementally is the catastrophic forgetting phenomenon. This phenomenon, which was discovered in the 90s, naturally occurs in Deep Learning architectures where classic learning paradigms are applied when learning incrementally from a stream of experiences. This dissertation revolves around the Continual Learning field, a sub-field of Machine Learning research that has recently made a comeback following the renewed interest in Deep Learning approaches. This work will focus on a comprehensive view of continual learning by considering algorithmic, benchmarking, and applicative aspects of this field. This dissertation will also touch on community aspects such as the design and creation of research tools aimed at supporting Continual Learning research, and the theoretical and practical aspects concerning public competitions in this field.

Computer vision in aseptic pharmaceutical manufacturing: a deep learning-based approach to vial inspection and pack formation during a lyophilizer loading cycle

Vision systems are powerful tools playing an increasingly important role in modern industry, to detect errors and maintain product standards. With the enlarged availability of affordable industrial cameras, computer vision algorithms have been increasingly applied in industrial manufacturing processes monitoring. Until a few years ago, industrial computer vision applications relied only on ad-hoc algorithms designed for the specific object and acquisition setup being monitored, with a strong focus on co-designing the acquisition and processing pipeline. Deep learning has overcome these limits providing greater flexibility and faster re-configuration. In this work, the process to be inspected consists in vials’ pack formation entering a freeze-dryer, which is a common scenario in pharmaceutical active ingredient packaging lines. To ensure that the machine produces proper packs, a vision system is installed at the entrance of the freeze-dryer to detect eventual anomalies with execution times compatible with the production specifications. Other constraints come from sterility and safety standards required in pharmaceutical manufacturing. This work presents an overview about the production line, with particular focus on the vision system designed, and about all trials conducted to obtain the final performance. Transfer learning, alleviating the requirement for a large number of training data, combined with data augmentation methods, consisting in the generation of synthetic images, were used to effectively increase the performances while reducing the cost of data acquisition and annotation. The proposed vision algorithm is composed by two main subtasks, designed respectively to vials counting and discrepancy detection. The first one was trained on more than 23k vials (about 300 images) and tested on 5k more (about 75 images), whereas 60 training images and 52 testing images were used for the second one.

Neuroarchitecture of the color and polarization vision system of the stomatopod haptosquilla

The apposition compound eyes of stomatopod crustaceans contain a morphologically distinct eye region specialized for color and polarization vision, called the mid-band. In two stomatopod superfamilies, the mid-band is constructed from six rows of enlarged ommatidia containing multiple photoreceptor classes for spectral and polarization vision. The aim of this study was to begin to analyze the underlying neuroarchitecture, the design of which might reveal clues how the visual system interprets and communicates to deeper levels of the brain the multiple channels of information supplied by the retina. Reduced silver methods were used to investigate the axon pathways from different retinal regions to the lamina ganglionaris and from there to the medulla externa, the medulla interna, and the medulla terminalis. A swollen band of neuropil-here termed the accessory lobe-projects across the equator of. the lamina ganglionaris, the medulla externa, and the medulla interna and represents, structurally, the retina's mid-band. Serial semithin and ultrathin resin sections were used to reconstruct the projection of photoreceptor axons from the retina to the lamina ganglionaris. The eight axons originating from one ommatidium project to the same lamina cartridge. Seven short visual fibers end at two distinct levels in each lamina cartridge, thus geometrically separating the two channels of polarization and spectral information. The eighth visual fiber runs axially through the cartridge and terminates in the medulla externa. We conclude that spatial, color, and polarization information is divided into three parallel data streams from the retina to the central nervous system. (C) 2003 Wiley-Liss, Inc.

Vision-based hand Wheel-chair control

Several studies have shown that people with disabilities benefit substantially from access to a means of independent mobility and assistive technology. Researchers are using technology originally developed for mobile robots to create easier to use wheelchairs. With this kind of technology people with disabilities can gain a degree of independence in performing daily life activities. In this work a computer vision system is presented, able to drive a wheelchair with a minimum number of finger commands. The user hand is detected and segmented with the use of a kinect camera, and fingertips are extracted from depth information, and used as wheelchair commands.

VLSI architecture for an Underwater Robot Vision System

It is well known that image processing requires a huge amount of computation, mainly at low level processing where the algorithms are dealing with a great number of data-pixel. One of the solutions to estimate motions involves detection of the correspondences between two images. For normalised correlation criteria, previous experiments shown that the result is not altered in presence of nonuniform illumination. Usually, hardware for motion estimation has been limited to simple correlation criteria. The main goal of this paper is to propose a VLSI architecture for motion estimation using a matching criteria more complex than Sum of Absolute Differences (SAD) criteria. Today hardware devices provide many facilities for the integration of more and more complex designs as well as the possibility to easily communicate with general purpose processors

Accuracy estimation of a new omnidirectional 3D vision sensor

We present a computer vision system that associates omnidirectional vision with structured light with the aim of obtaining depth information for a 360 degrees field of view. The approach proposed in this article combines an omnidirectional camera with a panoramic laser projector. The article shows how the sensor is modelled and its accuracy is proved by means of experimental results. The proposed sensor provides useful information for robot navigation applications, pipe inspection, 3D scene modelling etc

The Learning Affect Monitor (LAM) - A computer-based system integrating quantitative and qualitative assessment of affective states in daily life.

The Learning Affect Monitor (LAM) is a new computer-based assessment system integrating basic dimensional evaluation and discrete description of affective states in daily life, based on an autonomous adapting system. Subjects evaluate their affective states according to a tridimensional space (valence and activation circumplex as well as global intensity) and then qualify it using up to 30 adjective descriptors chosen from a list. The system gradually adapts to the user, enabling the affect descriptors it presents to be increasingly relevant. An initial study with 51 subjects, using a 1 week time-sampling with 8 to 10 randomized signals per day, produced n = 2,813 records with good reliability measures (e.g., response rate of 88.8%, mean split-half reliability of .86), user acceptance, and usability. Multilevel analyses show circadian and hebdomadal patterns, and significant individual and situational variance components of the basic dimension evaluations. Validity analyses indicate sound assignment of qualitative affect descriptors in the bidimensional semantic space according to the circumplex model of basic affect dimensions. The LAM assessment module can be implemented on different platforms (palm, desk, mobile phone) and provides very rapid and meaningful data collection, preserving complex and interindividually comparable information in the domain of emotion and well-being.

Computer-aided system for morphometric mandibular index computation (Using dental panoramic radiographs)

Objective: We propose and validate a computer aided system to measure three different mandibular indexes: cortical width, panoramic mandibular index and, mandibular alveolar bone resorption index. Study Design: Repeatability and reproducibility of the measurements are analyzed and compared to the manual estimation of the same indexes. Results: The proposed computerized system exhibits superior repeatability and reproducibility rates compared to standard manual methods. Moreover, the time required to perform the measurements using the proposed method is negligible compared to perform the measurements manually. Conclusions: We have proposed a very user friendly computerized method to measure three different morphometric mandibular indexes. From the results we can conclude that the system provides a practical manner to perform these measurements. It does not require an expert examiner and does not take more than 16 seconds per analysis. Thus, it may be suitable to diagnose osteoporosis using dental panoramic radiographs.

Computer-aided system for morphometric mandibular index computation (Using dental panoramic radiographs)

Objective: We propose and validate a computer aided system to measure three different mandibular indexes: cortical width, panoramic mandibular index and, mandibular alveolar bone resorption index. Study Design: Repeatability and reproducibility of the measurements are analyzed and compared to the manual estimation of the same indexes. Results: The proposed computerized system exhibits superior repeatability and reproducibility rates compared to standard manual methods. Moreover, the time required to perform the measurements using the proposed method is negligible compared to perform the measurements manually. Conclusions: We have proposed a very user friendly computerized method to measure three different morphometric mandibular indexes. From the results we can conclude that the system provides a practical manner to perform these measurements. It does not require an expert examiner and does not take more than 16 seconds per analysis. Thus, it may be suitable to diagnose osteoporosis using dental panoramic radiographs

Development of a systematic computer vision-based method to analyse and compare images of false identity documents for forensic intelligence purposes-Part I: acquisition, calibration and validation issues

Following their detection and seizure by police and border guard authorities, false identity and travel documents are usually scanned, producing digital images. This research investigates the potential of these images to classify false identity documents, highlight links between documents produced by a same modus operandi or same source, and thus support forensic intelligence efforts. Inspired by previous research work about digital images of Ecstasy tablets, a systematic and complete method has been developed to acquire, collect, process and compare images of false identity documents. This first part of the article highlights the critical steps of the method and the development of a prototype that processes regions of interest extracted from images. Acquisition conditions have been fine-tuned in order to optimise reproducibility and comparability of images. Different filters and comparison metrics have been evaluated and the performance of the method has been assessed using two calibration and validation sets of documents, made up of 101 Italian driving licenses and 96 Portuguese passports seized in Switzerland, among which some were known to come from common sources. Results indicate that the use of Hue and Edge filters or their combination to extract profiles from images, and then the comparison of profiles with a Canberra distance-based metric provides the most accurate classification of documents. The method appears also to be quick, efficient and inexpensive. It can be easily operated from remote locations and shared amongst different organisations, which makes it very convenient for future operational applications. The method could serve as a first fast triage method that may help target more resource-intensive profiling methods (based on a visual, physical or chemical examination of documents for instance). Its contribution to forensic intelligence and its application to several sets of false identity documents seized by police and border guards will be developed in a forthcoming article (part II).

Validation of a computer-assisted system on classifying lower third molars

Objectives: The present study evaluates the reliability of the Radio Memory® software (Radio Memory; Belo Horizonte,Brasil.) on classifying lower third molars, analyzing intra- and interexaminer agreement of the results. Study Design: An observational, descriptive study of 280 lower third molars was made. The corresponding orthopantomographs were analyzed by two examiners using the Radio Memory® software. The exam was repeated 30 days after the first observation by each examiner. Both intra- and interexaminer agreement were determined using the SPSS v 12.0 software package for Windows (SPSS; Chicago, USA). Results: Intra- and interexaminer agreement was shown for both the Pell & Gregory and the Winter classifications, p<0.01, with 99% significant correlation between variables in all the cases. Conclusions: The use of Radio Memory® software for the classification of lower third molars is shown to be a valid alternative to the conventional method (direct evaluation on the orthopantomograph), for both clinical and investigational applications.