Abstract-Detecting the camera model used to shoot a picture enables to solve a wide series of forensic problems, from copyright infringement to ownership attribution. For this reason, the forensic community has developed a set of camera model identification algorithms that exploit characteristic traces left on acquired images by the processing pipelines specific of each camera model. In this paper, we investigate a novel approach to solve camera model identification problem. Specifically, we propose a data-driven algorithm based on convolutional neural networks, which learns features characterizing each camera model directly from the acquired pictures. Results on a wellknown dataset of 18 camera models show that: (i) the proposed method outperforms up-to-date state-of-the-art algorithms on classification of 64x64 color image patches; (ii) features learned by the proposed network generalize to camera models never used for training.

Due to the wide diffusion of JPEG coding standard, the image forensic community has devoted significant attention to the development of double JPEG (DJPEG) compression detectors through the years. The ability of detecting whether an image has been compressed twice provides paramount information toward image authenticity assessment. Given the trend recently gained by convolutional neural networks (CNN) in many computer vision tasks, in this paper we propose to use CNNs for aligned and non-aligned double JPEG compression detection. In particular, we explore the capability of CNNs to capture DJPEG artifacts directly from images. Results show that the proposed CNN-based detectors achieve good performance even with small size images (i.e., 64 Ã\u97 64), outperforming state-of-the-art solutions, especially in the non-aligned case. Besides, good results are also achieved in the commonly-recognized challenging case in which the first quality factor is larger than the second one

No abstract

No abstract

Pedestrian detection is a popular research topic due to its paramount importance for a number of applications, especially in the fields of automotive, surveillance and robotics. Despite the significant improvements, pedestrian detection is still an open challenge that calls for more and more accurate algorithms. In the last few years, deep learning and in particular convolutional neural networks emerged as the state of the art in terms of accuracy for a number of computer vision tasks such as image classification, object detection and segmentation, often outperforming the previous gold standards by a large margin. In this paper, we propose a pedestrian detection system based on deep learning, adapting a general-purpose convolutional network to the task at hand. By thoroughly analyzing and optimizing each step of the detection pipeline we propose an architecture that outperforms traditional methods, achieving a task accuracy close to that of state-of-the-art approaches, while requiring a low computational time. Finally, we tested the system on an NVIDIA Jetson TK1, a 192-core platform that is envisioned to be a forerunner computational brain of future self-driving cars.

No abstract

Camera model identification is paramount to verify image origin and authenticity in a blind fashion. State-of-the-art techniques leverage the analysis of features describing characteristic footprints left on images by different camera models from the image acquisition pipeline (e.g., traces left by proprietary demosaicing strategies, etc.). Motivated by the very accurate performance achieved by feature-based methods, as well as by the progress brought by deep architectures in machine learning, we explore in this paper the possibility of taking advantage of convolutional neural networks (CNNs) for camera model identification. More specifically, we investigate: (i) the capability of different network architectures to learn discriminant features directly from the observed images; (ii) the dependency between the amount of training data and the achieved accuracy; (iii) the importance of selecting a correct protocol for training, validation and testing. This study shows that promising results can be obtained on small image patches training a CNN with an affordable setup (i.e., a personal computer with one dedicated GPU) in a reasonable amount of time (i.e., approximately one hour), given that a sufficient amount of training images is available. Conv-1 (32) Conv-1 (32) Conv-1 (32) Conv-1 (32) Conv-1 (32) Conv-1 (32) Conv-1 (32) Pool-1 Conv-2 (48) Conv-2 (48) Conv-2 (48) Conv-2 (48) Conv-2 (48) Conv-2 (48) Conv-2 (48) Pool-2 Conv-3 (64) Conv-3 (64) Conv-3 (64) Conv-3 (64) Conv-3 (64) Conv-3 (64) Conv-3 (64) Pool-3 Conv-4 (128) Conv-4 (128) Conv-4 (128) Conv-4 (128) Conv-4 (128) Conv-4 (128) Conv-4 (128) InnerProduct-1 ReLU-1 InnerProduct-2 SoftMax

Abstract-Technology is quickly revolutionizing our everyday lives, helping us to perform complex tasks. The Internet of Things (IoT) paradigm is getting more and more popular and is key to the development of Smart Cities. Among all the applications of IoT in the context of Smart Cities, realtime parking lot occupancy detection recently gained a lot of attention. Solutions based on computer vision yield good performance in terms of accuracy and are deployable on top of visual sensor networks. Since the problem of detecting vacant parking lots is usually distributed over multiple cameras, adhoc algorithms for content acquisition and transmission are to be devised. A traditional paradigm consists in acquiring and encoding images or videos and transmitting them to a central controller, which is responsible for analyzing such content. A novel paradigm, which moves part of the analysis to sensing devices, is quickly becoming popular. We propose a system for distributed parking lot occupancy detection based on the latter paradigm, showing that onboard analysis and transmission of simple features yield better performance with respect to the traditional paradigm in terms of the overall rate-energyaccuracy performance.