Oliver Giudice

Aligning shapes for symbol classification and retrieval

This paper proposes a method able to exploit peculiarities of both, local and global shape descriptors, to be employed for shape classification and retrieval. In the proposed framework, the silhouettes of symbols are firstly described through Bags of Shape Contexts. The shape signature is then used to solve the correspondence problem between points of two shapes. The obtained correspondences are employed to recover the geometric transformations between the shape to be classified/retrieved and the ones belonging to the training dataset. The alignment is based on a voting procedure in the parameter space of the model considered to recover the geometric transformation. The aligned shapes are finally described with the Blurred Shape Model descriptor for classification and retrieval purposes. Experimental results demonstrate the effectiveness of the proposed solution on two classic benchmark shape datasets, as well as on a large scale set of hand sketches composed by 20,000 examples distributed over 250 object categories.

Road Traffic Conflict Analysis from Geo-referenced Stereo Sequences

In this paper an imaging system for road traffic conflict analysis is proposed. The system exploits geo-referenced stereo sequences and tracking procedure to compute traffic conflict measures which can be analysed by experts. Using the potentiality of the traffic conflict technique as a surrogate safety measure could constitute an effective tool in understanding how the driver interacts and adapts its behaviour with respect to the vehicle, the road characteristics, the traffic control devices and environment. Experiments performed on real data acquired in urban environment confirm the effectiveness of the system which makes simple and fast for the experts the understanding of the driver behaviour.

A Classification Engine for Image Ballistics of Social Data.

Image Forensics has already achieved great results for the source camera identification task on images. Standard approaches for data coming from Social Network Platforms cannot be applied due to different processes involved (e.g., scaling, compression, etc.). In this paper, a classification engine for the reconstruction of the history of an image, is presented. Specifically, machine learning techniques and a-priori knowledge acquired through image analysis, we propose an automatic approach that can understand which Social Network Platform has processed an image and the software application used to perform the image upload. The engine makes use of proper alterations introduced by each platform as features. Results, in terms of global accuracy on a dataset of 2720 images, confirm the effectiveness of the proposed strategy.

Multimedia Forensics: discovering the history of multimedia contents

Multimedia Forensics is devoted to analyse digital multimedia contents such as photo, video and audio in order to produce evidences in the forensics domain. Specifically Image Forensics focuses on investigating on still images by analysing the authenticity and integrity of data (Forgery Detection) and by reconstructing the history of the image itself since its acquisition (Image Ballistics). In this paper, a survey on image ballistics and forgery detection methods will be covered by presenting the most recent and promising approaches.

Vision based traffic conflict analysis

In this paper a vision based system for traffic conflict analysis is presented. The system employs geo-referenced stereo sequences and tracking procedure to provide much greater information regarding pre-crash and crash events than what is currently available. The exploitation of the traffic conflict technique potentiality as a surrogate safety measure could constitute an effective tool in understanding how the driver interacts and adapts its behavior with respect to the vehicle, the road characteristics, the traffic control devices and the environment. Experiments performed on real data acquired in urban context confirm the effectiveness of the system for the traffic conflicts measurement and the driver behavior analysis.

On-board monitoring system for road traffic safety analysis

Abstract This paper presents a framework for road traffic safety analysis. It is based on a stereo-vision system that, after being installed on-board of public transportation vehicles, collects data of what happens in front of a moving vehicle. The collected data are analysed throughout a process that acquire raw GPS information, video sequences and stereo-based depth maps to compute the surrogate safety measures. These measures are obtained by exploiting the Traffic Conflict Technique in conjunction with computer vision algorithms and a cascade of classifiers. The safety measures are then used for further analysis in order to identify dangerous locations in which an intervention is needed to improve the safety level and prevent accidents. Experiments performed in a real urban environment confirm the effectiveness of the framework.

Stereo Vision for Bus Traffic Conflict Investigation

In this paper an imaging system for bus traffic conflict investigation is presented. The system employs geo-referenced stereo sequences and tracking procedure to provide much greater information regarding pre-crash and crash events than what is currently available. The exploitation of the traffic conflict technique potentiality as a surrogate safety measure could constitute an effective tool in understanding how the driver interacts and adapts its behavior with respect to the vehicle, the road characteristics, the traffic control devices and the environment. Experiments performed on real data acquired in urban context confirm the effectiveness of the system for the traffic conflicts measurement and the driver behavior analysis.