Due to advancements in intelligent transportation and the emergence of automated vehicles, interest in analyzing driver behavior to improve commuters’ driving experiences has surged. Past studies have utilized driver gaze data to analyze behavior under various driving conditions using machine learning techniques. However, exploring driver behavior through multiple modalities can provide deeper insights. To this end, we conducted a naturalistic driver behavior study with ten participants, collecting vehicular data and driver gaze measurements using standard sensors. This dataset allows for an accurate assessment of driver behavior across different road types, traffic conditions, and congestion levels. Additionally, we investigated the influence of driving experience and time of day on behavior. Experienced drivers showed greater consistency across scenarios, while novices’ performance varied based on traffic intensity and route type.

Advancements in Intelligent Transportation Systems (ITS) enhance driver safety, comfort, and traffic flow. However, because human drivers remain integral to operating human-driven vehicles, their perception and attention are of significant importance in real-world traffic conditions. Previous studies have highlighted the increased accident susceptibility of novice drivers, but there has been limited research on how experience and perception affect each other. This study analyzes driver behavior in real-world traffic conditions based on driver experience, time of day, traffic congestion, and route familiarity. Our findings indicate that novice drivers exhibit lower spatial awareness, while intermediate drivers demonstrate improved awareness in moderate traffic. Conversely, experienced drivers consistently perform well across all conditions. Familiarity with routes enhances performance for all drivers, with experienced drivers adapting more quickly in unfamiliar situations. The study also contributes to existing data by providing continuous driver fixations in various driving scenarios and gaze-enhanced saliency maps, gaze-focused object detection, and saliency ranking to advance driver perception and autonomous vehicles.

Vehicular safety depends on road geometry and surface conditions that provide tire-terrain traction. Roads are constructed with 3-D features consisting of super-elevation, grade, horizontal profile. A driving automaton that is aware of these parameters and surface friction can make better driving decisions at optimal speeds that maintain vehicular stability. Estimation of tire-terrain friction requires a continuous 3-D surface. In order to satisfy these requirements, we extend the Open Curved Regular Grid (OpenCRG) format with a C2continuous surface that is dynamically generated at tire-terrain contact patches. We show that these estimates empower driving automatons to stably navigate curved elevated roads with super-elevated turns. We also show that sharing friction estimates using Basic Safety Messages (BSM) of Dedicated Short Range Communications (DSRC) can enable safety of following vehicles in control loss situations.

Vehicular subsystems such as Anti-lock braking (ABS), Traction Control System (TCS) and Electronic Stability Program (ESP) use low-level sensory data to maintain the vehicle's stability. We show that sharing that information with neighboring vehicles could prevent potential collisions. Towards achieving this goal, we propose extensions to Dedicated Short Range Communication (DSRC)'s Basic Safety Message (BSM) set and propose a controller which can use the transmitted information to avoid collisions with vehicles experiencing in-stabilities. We show the utility of our methodology by using 3 common lane change scenarios under varying road surface conditions. Finally, we demonstrate some limitations of our methodology using similar scenarios.

Activities of Daily Living (ADLs) are personal functional activities performed by individuals to carry out their daily lives, allowing them to live independently. Finding relationships between surface electromyograms (sEMG) measured in the arm and movements of the hand and wrist needed to perform ADLs can help address performance deficits and be exploited in designing myoelectric control systems. This paper reports on applying machine learning techniques to discover the electromyogram patterns present when using the hand to perform 47 typical fine motor functional activities used to accomplish ADLs. A Hidden Markov Model (HMM) combined with Random Forest (RF) classification is employed to learn the patterns needed to identify 10 second segments of continuous movement. The HMM/RF model was applied using two feature sets: one consisting entirely of sEMG signals, the other adding accelerometer data. Results show an accuracy improvement of the HMM/RF model over RF-only classification, and further improvement using the combined sEMG+ACC features, with a range of 74.99% to 84.09% and average of 79.06% for five subjects.

Today's world's societies are becoming more and more dependent on open networks such as the Internet – where commercial activities, business transactions, and government services are realized. This has led to the fast development of new cyber threats and numerous information security issues which are exploited by cyber criminals. The inability to provide trusted secure services in contemporary computer network technologies has a tremendous socio-economic impact on global enterprises as well as individuals. Moreover, the frequently occurring international frauds impose the necessity to conduct the investigation of facts spanning across multiple international borders. Such examination is often subject to different jurisdictions and legal systems. A good illustration of the previously mentioned is the Internet, which has made it easier to perpetrate traditional crimes. It has acted as an alternate avenue for the criminals to conduct their activities, and launch attacks with relative anonymity. The increased complexity of the communications and the networking infrastructure is making investigation of the crimes difficult. Traces of illegal digital activities are often buried in large volumes of data, which are hard to inspect with the aim of detecting offenses and collecting evidence. Nowadays, the digital crime scene functions like any other network, with dedicated administrators functioning as the first responders. This poses new challenges for law enforcement policies and forces the computer societies to utilize digital forensics to combat the increasing number of cybercrimes. Forensic professionals must be fully prepared in order to be able to provide court admissible evidence. To make these goals achievable, forensic techniques should keep pace with new technologies. In this special issue, we are delighted to present a selection of 14 papers, which, in our opinion, will contribute to the enhancement of knowledge in cyber crime. The collection of high-quality research papers provides a view on the latest research advances and results in the field of digital forensics and to present the development of tools and techniques which assist the investigation process of potentially illegal cyber activity. In the first paper, Cyberterrorism targeting the general public through social media, Nicholas Ayres and Leandros A. Maglaras investigate whether a mimetic malware could be a viable method of attack against a population with respect to cyberterrorism. The presented research shows that although people are, in general, aware of cyberterrorism on their current level of fear of being a potential target of attack is relatively low. However, when presented with such a threat, their level of fear increased. The obtained results prove that a targeted mimetic virus can indeed have an effect on a population and is a potential attack method for cyberterrorism. The paper emphasizes also the importance of social media as a vessel of propagation of such threat. Next, in the paper entitled Effectiveness of File-Based Deduplication in Digital Forensics Sebastian Neuner, Martin Schmiedecker, and Edgar Weippl focus on introducing improvements to the standardized forensic process to reduce the amount of storage requirement for forensic investigations by using file whitelisting and cross-device deduplication. Authors approach is shown to be particularly useful in cases where investigation relies on referenced files in the file system. In the exemplary use case authors prove that file deduplication and file whitelisting can be successfully utilized to achieve 78% size reduction compared to the full data set which means saving about 700 gigabytes of storage capacity. Jawwad Shamsi, Sherali Zeadally, Fareha Sheikh, and Angelyn Flowers in Attribution in Cyberspace: Techniques and Legal Implications argue that only a few known cybercrimes have been successfully attributed to the actual attacker. To improve this situation authors propose three-level attribution framework to indicate various attributes and guidelines through which attribution can be instigated. The proposed framework is an initial step and in order to be successful it requires strong cooperation between different stake holders, government sponsored active cyber unit, existence of cyber laws, and cooperation among international community members. Next, two papers are focused on anomaly detection. In Evolutionary-based Packets Classification for Anomaly Detection in Web Layer, Rafał Kozik, Michał Choraś, and Witold Hołubowicz propose a novel detection method for modern web applications. First, authors observe that the majority of the state of the art solutions make an assumption about the packets' content, or how the data inside the payload is serialized. Then they propose an evolutionary-based approach to unsupervised and automated packets segmentation. On the top of their approach, authors apply several variants of machine-learned classifiers and statistics to prove that the proposed algorithm can improve the effectiveness of many well-known anomaly detection methods. In the second paper entitled DWT-based Anomaly Detection Method for Cyber Security of Wireless Sensor Networks Łukasz Saganowski, Tomasz Andrysiak, Rafał Kozik, and Michał Choraś introduce a discrete wavelet transformation-based anomaly detection approach for wireless sensor networks which is especially suited for deployment in critical infrastructures for measuring and/or monitoring purposes. The main authors' contribution is that the proposed anomaly detection is integrated with an effective SNORT-based pre-processor. Then DWT-based solution is applied to 25 network traffic parameters measured in a realistic testbed and most suitable parameters are indicated. It is worth noting that several papers from this special issue are devoted to information hiding techniques, which utilization is currently a raising trend among cybercriminals. Papers focus on both: proposing new methods and detection approaches. In the first paper entitled Pitch-based steganography for Speex voice codec, Artur Janicki devises an improved version of the HideF0 steganographic algorithm which is especially suitable for IP telephony. The proposed approach relies on approximation of the pitch-related parameter (F0) in speech signal regions where the pitch is monotonic enough to be linearly approximated with a low error. It also utilizes unused fields in the headers of the voice packets. Experiments conducted on all narrowband Speex codec modes show that an improvement in quality when compared with the originally proposed algorithm has been observed. The resulting steganographic bandwidths of HideF0 turns out to be around 200 bps at the expense of a steganographic cost of between 0.5 and 0.7 MOS, depending on the Speex mode. Hui Tian, Yanpeng Wu, Chin-Chen Chang, Yongfeng Huang, Jin Liu, Tian Wang, Yonghong Chen, and Yiqiao Cai in Steganalysis of Analysis-by-synthesis Speech Exploiting Pulse-position Distribution Characteristics introduce a Support Vector Machine-based detection of low bit-rate speech which utilizes statistic characteristics of pulse positions, that is, the probability distribution of pulse positions as a long-time distribution feature, Markov transition probabilities of pulse positions according to the short-time invariance characteristic of speech signals, and finally joint probability matrices characterizing the pulse-to-pulse correlation. The proposed steganalysis method is evaluated for the G.729a speech codec and compared with the state-of-the-art methods. Obtained experimental results reveal that the proposed method's detection performance is superior when compared with the previous steganalysis algorithms. The paper, Color Images Stegananalysis Using RGB Channel Geometric Transformation Measures by Hasan Abdulrahman, Marc Chaumont, Philippe Montesinos, and Baptiste Magnier, introduces steganalysis method for color images that is based on color feature correlation and machine learning classification. This approach relies on fusing features with those obtained from color-rich models which results in improved detectability of hidden messages. Authors use two types of features, computed between color image channels – first that reflects local Euclidean transformations and second that reflects mirror transformations. They also demonstrate the efficiency of the proposed detection method on three state-of-the-art steganography algorithms. The paper, A framework of adaptive steganography resisting JPEG compression and detection by Yi Zhang, Xiangyang Luo, Chunfang Yang, Dengpan Ye, and Fenlin Liu, describes a framework of adaptive steganography resisting JPEG compression and detection which aims at solving the issue of information loss in the process of image compression while applying image steganography to mobile intelligent terminals. The proposed framework uses the relationship between discrete cosine transform coefficients to determine the domain of messages embedding. Based on this framework, authors devise an adaptive steganography algorithm and perform its evaluation. Obtained experimental results for different payloads and quality factors of JPEG compression prove that when an algorithm is based on the framework, it has both a strong JPEG compression resistant ability and detection resistant performance. In the next paper, Micro protocol engineering for unstructured carriers: On the embedding of steganographic control protocols into audio transmissions, Matthias Naumann, Steffen Wendzel, Wojciech Mazurczyk, and Jörg Keller present techniques to embed micro protocol, that is, covert channel control protocol into an unstructured carrier which is audio streaming over the network. Two types of implementing the micro protocol: static and dynamic have been demonstrated. This allowed comparing the resulting performance and to measure the impact of both designs on the overt audio signal. On the basis of obtained experimental results, a micro protocol engineering approach for unstructured carriers has been devised. Another paper that is focused on analysis of micro protocols has been authored by Jaspreet Kaur, Steffen Wendzel, Omar Eissa, Jernej Tonejc, and Michael Meier. In Covert Channel-internal Control Protocols: Attacks and Defense, an interesting analysis of micro protocols has been conducted. First authors demonstrate that some potential attacks scenarios on micro protocols exist, and that if successful, they are able to break even sophisticated covert communication. The described attacks are based on the attacker's intentional interaction with the micro protocol specifics. Then, authors propose several defense techniques to make micro protocols immune against such threats. In Perfect undetectability of network steganography, Wojciech Frączek and Krzysztof Szczypiorski introduce StegBlocks that is a general approach for constructing network steganography techniques which defines the way in which the methods work, and at the same time it allows for the creation of methods for various carriers (network protocols). The paper encloses also the definition of perfectly undetectable network steganography which is derived from a classic steganography definition, and it covers the specific features of network steganography. Using this definition, authors argue that it is possible to create a network steganography method that is undetectable for the adversary with unlimited computational power. In the next article, DAT Detectors – Uncovering TCP/IP Covert Channels by Descriptive Analytics, Felix Iglesias, Robert Annessi, and Tanja Zseby propose descriptive analytics of traffic (DAT) detectors that utilize descriptive analytics for the detection of covert channels in TCP/IP communication networks. DAT detectors are envisioned to be an extension for network intrusion detection system and are aimed to perform fast and lightweight analysis of numerous flows. They transform communication data into flexible feature vectors that represent traffic as a set of extracted calculations and estimations. The detection approach relies mostly on the combined application of autocorrelation calculations and multimodality measures built upon kernel density estimations and Pareto charts. In the last of the presented articles, An assessment of automatic speaker verification vulnerabilities to replay spoofing attacks, Artur Janicki, Federico Alegre, and Nicholas Evans compare at a high level the threat of replay attacks to those of speech synthesis and voice conversion. This comparison is performed using strictly controlled protocols and with six different Automatic Speaker Verification systems. Presented experimental results prove that low-effort replay attacks are indeed a threat to speech synthesis and voice conversion. Basing on these findings, authors also introduce and assess two replay attack countermeasures: the local binary pattern analysis of speech spectrograms and an approach based on the detection of far-fields recordings. To summarize, we believe that this Special Issue will contribute to enhancing knowledge in Information and Communication Technology security and in Cyber Crime in particular. In addition, we also hope that the presented results will stimulate further research in the important areas of information and network security. We also want to thank the Editors-in-Chief of the Security and Communication Networks journal, the researchers contributing to the special issue, and excellent reviewers for their great help and support that made this special issue possible.

People want to live independently, but too often disabilities or advanced age robs them of the ability to do the necessary activities of daily living (ADLs). Finding relationships between electromyograms measured in the arm and movements of the hand and wrist needed to perform ADLs can help address performance deficits and be exploited in designing myoelectrical control systems for prosthetics and computer interfaces. This paper reports on several machine learning techniques employed to discover the electromyogram patterns present when using the hand to perform 14 typical fine motor functional activities used to accomplish ADLs. Classification and clustering techniques are employed. Improvements to accuracies are introduced, including the use of exponential smoothing and using a symbolic representation to approximate signal streams. Results show the patterns can be learned to an accuracy of approximately 77% for a 15 class problem and the symbolic representation shows the potential for future improvement in accuracies.

Source code plagiarism is an easy to do task, but very difficult to detect without proper tool support. Various source code similarity detection systems have been developed to help detect source code plagiarism. Those systems need to recognize a number of lexical and structural source code modifications. For example, by some structural modifications (e.g. modification of control structures, modification of data structures or structural redesign of source code) the source code can be changed in such a way that it almost looks genuine. Most of the existing source code similarity detection systems can be confused when these structural modifications have been applied to the original source code. To be considered effective, a source code similarity detection system must address these issues. To address them, we designed and developed the source code similarity system for plagiarism detection. To demonstrate that the proposed system has the desired effectiveness, we performed a well-known conformism test. The proposed system showed promising results as compared with the JPlag system in detecting source code similarity when various lexical or structural modifications are applied to plagiarized code. As a confirmation of these results, an independent samples t-test revealed that there was a statistically significant difference between average values of F-measures for the test sets that we used and for the experiments that we have done in the practically usable range of cut-off threshold values of 35–70%.

We have developed engaging virtual environments using haptic technology for the purpose of both understanding functional activity and restoring functionality to disabled individuals. To assess our virtual environments, we used 21 able-bodied subjects and examined their motor performance by comparing several metrics captured by the simulations to the completion time. We discovered that individuals were highly engaged during our simulation, and the motor performance across subjects improved with each repeated trial. We showed how to use motor performance metrics that can be captured by the device can accurately predict completion time. We also developed several metrics for estimating object interaction difficulty.

The goal of our research is to design a haptic-based system to assist people with disabilities in learning functional motor tasks. Specifically, we are studying the upper extremity while performing daily activities. We have explored fine motor activities, such as writing, and gross motor activities, such as feeding and grooming. We use electromagnetic sensors (MotionStar Wireless 2) to capture unencumbered movements performed by a 'normal' individual. The captured movement is translated to the haptic coordinate system with the use of a body centered, intermediate frame for gross motor activities and with the use of a table-top centered frame for fine motor activities. We segment the movement into simple strokes and then 'smooth' the strokes using low pass filtering, cubic spline fitting and polynomial curve fitting. Our system varies the haptic force as the function of performance of the trainee. We have used our method to program the Phantom Omni for writing tasks and the Phantom Premium 3.0/6 DoF for gross motor tasks. We demonstrate our methodology with several examples of fine and gross functional activities.

We propose a novel method for predicting whether an image taken from a given location will match an existing set of images. This problem appears prominently in image based localization and augmented reality applications where new images are matched to an existing set to determine location or add virtual information into a scene. Our process generates a spatial coverage map showing the confidence that images taken at specific locations will match an existing image set. A new way to measure distortion between images using affine models is introduced. The distortion measure is combined with existing machine learning and structure from motion techniques to create a matching confidence predictor. The predictor is used to generate the spatial coverage map and also compute which images in the original set are redundant and can be removed. Results are presented showing the predictor is more accurate than previously published approaches.

A method to classify tentative feature matches as inliers or outliers to a transformation model is presented. It is well known that ratios of areas of corresponding shapes are affine invariants. Our algorithm uses consistency of ratios of areas in pairs of images to classify matches as inliers or outliers. The method selects four matches within a region, and generates all possible corresponding triangles. All matches are classified as inliers or outliers based on the variance among the ratio of areas of the triangles. The selected inliers are used to compute a homography transformation. We present experimental results showing significant improvements over the baseline RANSAC algorithm for pairs of images from the Zurich Building Database.

The goal of our demonstration is to illustrate how the haptic, force feedback device, can be used to assist people with disabilities in learning fine motor tasks, such as writing. We will be demonstrating this idea by the simulation of several letters and symbols. We use electromagnetic sensors (MotionStar Wireless2) to capture unencumbered movements performed by a 'normal' individual. The captured movement is translated to the haptic coordinate system with the use of a table-top centered frame as an intermediate frame. The translated movement is then fed into our haptic system, which varies the exerted force as a function of trainee performance. Our demonstration will use the Phantom Omni for the simulation of these writing tasks, and it will also provide visual feedback of the desired and user trajectories.

We propose a novel approach to gait analysis using the independent components of motion. Our motion representation uses the amount of translation in small image patches. For each subject in the training set, several short image sequences are selected at random. Spatiotemporal independent component analysis (stICA) estimates independent components (ICs) of the training sequences. Given an unknown subject, we compute stIC coefficients for all image subsequences. These coefficients are compared with the training set using the cosine similarity measure. We demonstrate feasibility by using the nearest neighbor to classify the gender of a subject.

Static computer vision techniques enable non-intrusive observation and analysis of biometrics such as eye blinks. However, ambiguous eye behaviors such as partial blinks and asymmetric eyelid movements present problems that computer vision techniques relying on static appearance alone cannot solve reliably. Image flow analysis enables reliable and efficient interpretation of these ambiguous eye blink behaviors. In this paper we present a method for using image flow analysis to compute problematic eye blink parameters. The flow analysis produces the magnitude and direction of the eyelid movement. A deterministic finite state machine uses the eyelid movement data to compute blink parameters (e.g., blink count, blink rate, and other transitional statistics) for use in human computer interaction applications across a wide range of disciplines. We conducted extensive experiments employing this method on approximately 750K color video frames of five subjects

The motion of an articulated object can be very complex but the motions of its rigid parts are usually simple. Here a method is proposed to classify and segment the motion of an articulated object into simple motions in temporal and spatial domains. Simple motions are represented by the corresponding motion flow patterns. Both the motion detection and segmentation are accomplished by matching the flow patterns of known simple motions with image flow. Matching is done by comparing the parametric flows of motion patterns with the normal flows of a target image. The approach is demonstrated on several image sequences of moving arms

This paper describes a novel application of Statistical Learning Theory (SLT) to single motion estimation and tracking. The problem of motion estimation can be related to statistical model selection, where the goal is to select one (correct) motion model from several possible motion models, given finite noisy samples. SLT, also known as Vapnik-Chervonenkis (VC), theory provides analytic generalization bounds for model selection, which have been used successfully for practical model selection. This paper describes a successful application of an SLT-based model selection approach to the challenging problem of estimating optimal motion models from small data sets of image measurements (flow). We present results of experiments on both synthetic and real image sequences for motion interpolation and extrapolation; these results demonstrate the feasibility and strength of our approach. Our experimental results show that for motion estimation applications, SLT-based model selection compares favorably against alternative model selection methods, such as the Akaike's fpe, Schwartz' criterion (sc), Generalized Cross-Validation (gcv), and Shibata's Model Selector (sms). The paper also shows how to address the aperture problem using SLT-based model selection for penalized linear (ridge regression) formulation.

Man made indoor environments possess regularities, which can be efficiently exploited in automated model acquisition by means of visual sensing. In this context we propose an approach for inferring a topological model of an environment from images or the video stream captured by a mobile robot during exploration. The proposed model consists of a set of locations and neighborhood relationships between them. Initially each location in the model is represented by a collection of similar, temporally adjacent views, with the similarity defined according to a simple appearance based distance measure. The sparser representation is obtained in a subsequent learning stage by means of learning vector quantization (LVQ). The quality of the model is tested in the context of qualitative localization scheme by means of location recognition: given a new view, the most likely location where that view came from is determined.

This paper describes technology and tools for intelligent human-computer interaction (IHCI) in which human cognitive, perceptual, motor and affective factors are modeled and used to adapt the H-C interface. IHCI emphasizes that human behavior encompasses both apparent human behavior and the hidden mental state behind behavioral performance. IHCI expands on the interpretation of human activities, known as W4 (what, where, when, who). While W4 only addresses the apparent perceptual aspect of human behavior the W5+ technology for IHCI described in this paper addresses also the why and how questions, whose solution requires recognizing specific cognitive states. IHCI integrates parsing and interpretation of nonverbal information with a computational cognitive model of the user which, in turn, feeds into processes that adapt the interface to enhance operator performance and provide for rational decision-making. The technology proposed is based on a general four-stage interactive framework, which moves from parsing the raw sensory-motor input, to interpreting the user's motions and emotions, to building an understanding of the user's current cognitive state. It then diagnoses various problems in the situation and adapts the interface appropriately. The interactive component of the system improves processing at each stage. Examples of perceptual, behavioral, and cognitive tools are described throughout the paper Adaptive and intelligent HCI are important for novel applications of computing, including ubiquitous and human-centered computing.

A computer vision system for tracking multiple people in relatively unconstrained environments is described. Tracking is performed at three levels of abstraction: regions, people and groups. A novel, adaptive background subtraction method that combines colour and gradient information is used to cope with shadows and unreliable colour cues. People are tracked through mutual occlusions as they form groups and part from one another. Strong use is made of colour information to disambiguate occlusions and to provide qualitative estimates of depth ordering and position during occlusion. Some simple interactions with objects can also be detected. The system is tested using indoor and outdoor sequences. It is robust and should provide a useful mechanism for bootstrapping and reinitialisation of tracking using more-specific but less-robust human models.

If we histogram the normal flow vectors in images of a scene viewed by a moving observer, we can use the time-varying histogram to derive qualitative information about the observer's motion-for example, whether it is (primarily) translational or rotational, and whether the direction of translation or axis of rotation is (roughly) parallel or perpendicular to the camera axis. This is illustrated using flow histogram obtained from a variety of real image sequences.

A new method of finding people in video images is presented. The detection is based on a novel background modeling and subtraction approach which uses both color and edge information. We introduce confidence maps gray-scale images whose intensity is a function of confidence that a pixel has changed - to fuse intermediate results and represent the results of background subtraction. The latter is used to delineate a person's body by guiding contour collection to segment the person from the background. The method is tolerant to scene clutter, slow illumination changes, and camera noise, and runs in near real time on a standard platform.

Many types of common objects, such as tools and vehicles, usually move in simple ways when they are wielded or driven. The natural axes of the object tend to remain aligned with the local trihedron defined by the object's trajectory. Based on this observation we use a model called Frenet-Serret motion which corresponds to the motion of a moving trihedron along a space curve. Knowing how the Frenet-Serret frame is changing relative to the observer gives us essential information for understanding the object's motion. This is illustrated here for four examples, involving tools (a wrench and a saw) and vehicles (an accelerating van, a turning taxi).

In order for a robot to operate autonomously in its environment, it must be able to perceive its environment and take actions based on these perceptions. Recognizing the functionalities of objects is an important component of this ability. In this paper, we look into a new area of functionality recognition: determining the function of an object from its motion. Given a sequence of images of a known object performing some function, we attempt to determine what that function is. We show that the motion of an object, when combined with information about the object and its normal uses, provides us with strong constraints on possible functions that the object might be performing.

A new model, Frenet-Serret motion, is proposed for the motion of an observer in a stationary environment. This model relates the motion parameters of the observer to the curvature and torsion of the path along which the observer moves. Screw-motion equations for Frenet-Serret motion are derived and employed for geometrical analysis of the motion. Normal flow is used to derive constraints on the rotational and translational velocity of the observer and to compute egomotion by intersecting these constraints in the manner proposed by Z. Duric/spl acute/ and Y. Aloimonos (1989). The accuracy of egomotion estimation is analyzed for different combinations of observer motion and feature distance. The authors explain the advantages of controlling feature distance to analyze egomotion and derive the constraints on depth which make either rotation or translation dominant in the perceived normal flow field. The results of experiments on real image sequences are presented.>