Search

Dense optical flow estimation is complex and time consuming, with state-of-the-art methods relying either on large synthetic data sets or on pipelines requiring up to a few minutes per frame pair. In this paper, we address the problem of optical flow estimation in the automotive scenario in a self-supervised manner. We argue that optical flow can be cast as a geometrical warping between two successive video frames and devise a deep architecture to estimate such transformation in two stages. First, a dense pixel-level flow is computed with a projective bootstrap on rigid surfaces. We show how such global transformation can be approximated with a homography and extend spatial transformer layers so that they can be employed to compute the flow field implied by such transformation. Subsequently, we refine the prediction by feeding a second, deeper network that accounts for moving objects. A final reconstruction loss compares the warping of frame $X_{t}$ with the subsequent frame $X_{t+1}$ and guides both estimates. The model has the speed advantages of end-to-end deep architectures while achieving competitive performances, both outperforming recent unsupervised methods and showing good generalization capabilities on new automotive data sets.

With the rapid increase of outdoor computer vision applications requiring robustness to adverse weather conditions such as automotive and robotics, the loss in image quality that is due to raindrops adherent to the camera lenses is becoming a major concern. In this paper we propose to remove raindrops and improve image quality in the spatio-temporal domain by leveraging the inherent robustness of adopting motion cues and the restorative capabilities of conditional generative adversarial networks. We first propose a competitive single-image baseline capable of estimating the raindrop locations in a self-supervised manner, and then use it to bootstrap our novel spatio-temporal architecture. This shows encouraging performance when compared to both state of the art single-image de-raining methods, and recent video-to-video translation approaches.

The Internet of Things, whose main goal is to automatically predict users' desires, can find very interesting opportunities in the art and culture field, as the tourism is one of the main driving engines of the modern society. Currently, the innovation process in this field is growing at a slower pace, so the cultural heritage is a prerogative of a restricted category of users. To address this issue, a significant technological improvement is necessary in the culture-dedicated locations, which do not usually allow the installation of hardware infrastructures. In this paper, we design and validate a no-invasive indoor location-aware architecture able to enhance the user experience in a museum. The system relies on the user's smartphone and a wearable device (with image recognition and localization capabilities) to automatically deliver personalized cultural contents related to the observed artworks. The proposal was validated in the MUST museum in Lecce (Italy).

In this chapter we address the problem of partitioning social gatherings into interacting groups in egocentric scenarios. People in the scene are tracked, and their head pose and 3D location are estimated. Following the formalism of the f-formation, we define as regards the orientation and distance inherently social pairwise features capable of describing how two people stand in relation to one another. We present a structural SVM-based approach to learn how to weight each component of the feature vector depending on the social situation being applied to. To better understand the social dynamics, we also estimate what we call the social relevance of each subject in a group using a saliency attentive model. Extensive tests on two publicly available datasets show that our solution achieves encouraging results when detecting social groups and their relevant subjects in challenging egocentric scenarios.

Despite the advent of autonomous cars, it's likely - at least in the near future - that human attention will still maintain a central role as a guarantee in terms of legal responsibility during the driving task. In this paper we study the dynamics of the driver's gaze and use it as a proxy to understand related attentional mechanisms. First, we build our analysis upon two questions: where and what the driver is looking at? Second, we model the driver's gaze by training a coarse-to-fine convolutional network on short sequences extracted from the DR(eye)VE dataset. Experimental comparison against different baselines reveal that the driver's gaze can indeed be learnt to some extent, despite i) being highly subjective and ii) having only one driver's gaze available for each sequence due to the irreproducibility of the scene. Eventually, we advocate for a new assisted driving paradigm which suggests to the driver, with no intervention, where she should focus her attention., Comment: To appear in IEEE Intelligent Vehicles Symposium 2017

With the spread of wearable cameras, many consumer applications ranging from social tagging to video summarization would greatly benefit from people re-identification methods capable of dealing with the egocentric perspective. In this regard, first-person camera views present such a unique setting that traditional re-identification methods results in poor performance when applied to this scenario. In this paper, we present a simple but effective solution that overcomes the limitations of traditional approaches by dividing people images into meaningful body parts. Furthermore, by taking into account human gaze information concerning where people look at when trying to recognize a person, we devise a meaningful way to weight the contributions of different bodyparts. Experimental results validate the proposal on a novel egocentric re-identification dataset, the first of its kind, showing that the performance increases when compared to current state of the art on egocentric sequences is significant.

Autonomous and assisted driving are undoubtedly hot topics in computer vision. However, the driving task is extremely complex and a deep understanding of drivers' behavior is still lacking. Several researchers are now investigating the attention mechanism in order to define computational models for detecting salient and interesting objects in the scene. Nevertheless, most of these models only refer to bottom up visual saliency and are focused on still images. Instead, during the driving experience the temporal nature and peculiarity of the task influence the attention mechanisms, leading to the conclusion that real life driving data is mandatory. In this paper we propose a novel and publicly available dataset acquired during actual driving. Our dataset, composed by more than 500,000 frames, contains drivers' gaze fixations and their temporal integration providing task-specific saliency maps. Geo-referenced locations, driving speed and course complete the set of released data. To the best of our knowledge, this is the first publicly available dataset of this kind and can foster new discussions on better understanding, exploiting and reproducing the driver's attention process in the autonomous and assisted cars of future generations.

The Internet of Things, whose main goal is to automatically predict users' desires, can find very interesting opportunities in the art and culture field, as the tourism is one of the main driving engines of the modern society. Currently, the innovation process in this field is growing at a slower pace, so the cultural heritage is a prerogative of a restricted category of users. To address this issue, a significant technological improvement is necessary in the culture-dedicated locations, which do not usually allow the installation of hardware infrastructures. In this paper, we design and validate a no-invasive indoor location-aware architecture able to enhance the user experience in a museum. The system relies on the user's smartphone and a wearable device (with image recognition and localization capabilities) to automatically deliver personalized cultural contents related to the observed artworks. The proposal was validated in the MUST museum in Lecce (Italy).

With the spread of wearable and mobile devices, the request for interactive augmented reality applications is in constant growth. Among the different possibilities, we focus on the cultural heritage domain where a key step in the development applications for augmented cultural experiences is to obtain a precise localization of the user, i.e. the 6 degree-of-freedom of the camera acquiring the images used by the application. Current state of the art perform this task by extracting local descriptors from a query and exhaustively matching them to a sparse 3D model of the environment. While this procedure obtains good localization performance, due to the vast search space involved in the retrieval of 2D-3D correspondences this is often not feasible in real-time and interactive environments. In this paper we hence propose to perform descriptor quantization to reduce the search space and employ multiple KD-Trees combined with a principal component analysis dimensionality reduction to enable an efficient search. We experimentally show that our solution can halve the computational requirements of the correspondence search with regard to the state of the art while maintaining similar accuracy levels.

The interest in cultural cities is in constant growth, and so is the demand for new multimedia tools and applications that enrich their fruition. In this paper we propose an egocentric vision system to enhance tourists' cultural heritage experience. Exploiting a wearable board and a glass-mounted camera, the visitor can retrieve architectural details of the historical building he is observing and receive related multimedia contents. To obtain an effective retrieval procedure we propose a visual descriptor based on the covariance of local features. Differently than the common Bag of Words approaches our feature vector does not rely on a generated visual vocabulary, removing the dependence from a specific dataset and obtaining a reduction of the computational cost. 3D modeling is used to achieve a precise visitor's localization that allows browsing visible relevant details that the user may otherwise miss. Experimental results conducted on a publicly available cultural heritage dataset show that the proposed feature descriptor outperforms Bag of Words techniques.

Smart cities are a trading topic in both the academic literature and industrial world. The capability to provide the users with added- value services through low-power and low-cost smart objects is very attractive in many fields. Among these, art and culture represent very interesting examples, as the tourism is one of the main driving engines of modern society. In this paper, we propose an IoT-aware architecture to improve the cultural experience of the user, by involving the most important recent innovations in the ICT field. The main components of the proposed architecture are: (i) an indoor localization service based on the Bluetooth Low Energy technology, (ii) a wearable device able to capture and process images related to the user’s point of view, (iii) the user’s mobile device useful to display customized cultural contents and to share multimedia data in the Cloud, and (iv) a processing center that manage the core of the whole business logic. In particular, it interacts with both wearable and mobile devices, and communicates with the outside world to retrieve contents from the Cloud and to provide services also to external users. The proposal is currently under development and it will be validated in the MUST museum in Lecce.

The understanding of mutual people interaction is a key component for recognizing people social behavior, but it strongly relies on a personal point of view resulting difficult to be a-priori modeled. We propose the adoption of the unique head mounted cameras first person perspective (ego-vision) to promptly detect people interaction in different social contexts. The proposal relies on a complete and reliable system that extracts people's head pose combining landmarks and shape descriptors in a temporal smoothed HMM framework. Finally, interactions are detected through supervised clustering on mutual head orientation and people distances exploiting a structural learning framework that specifically adjusts the clustering measure according to a peculiar scenario. Our solution provides the flexibility to capture the interactions disregarding the number of individuals involved and their level of acquaintance in context with a variable degree of social involvement. The proposed system shows competitive performances on both publicly available ego-vision datasets and ad hoc benchmarks built with real life situations. HighlightsA head pose estimation method designed to work in ego-vision scenarios is provided.We define a 3D people localization method that works without any camera calibration.We estimate social groups with supervised correlation clustering and structural SVM.A tracking state-of-the-art evaluation applied to first person videos is provided.

In this paper we present a new method for head pose real-time estimation in ego-vision scenarios that is a key step in the understanding of social interactions. In order to robustly detect head under changing aspect ratio, scale and orientation we use and extend the Hough-Based Tracker which allows to follow simultaneously each subject in the scene. In an ego-vision scenario where a group interacts in a discussion, each subject's head orientation will be more likely to remain focused for a while on the person who has the floor. In order to encode this behavior we include a stateful Hidden Markov Model technique that enforces the predicted pose with the temporal coherence from a video sequence. We extensively test our approach on several indoor and outdoor ego-vision videos with high illumination variations showing its validity and outperforming other recent related state of the art approaches.