92 research outputs found
Sustainable Small-Scale Marine Fishing Resources and Communities in Kerala, India - Policy makers
No full textSustainable Small-Scale Marine Fishing Resources and Communities in Kerala, India - Extension
No full textSustainable Small-Scale Marine Fishing Resources and Communities in Kerala, India - Resarchers
No full textJPEG Fake Media: a provenance-based sustainable approach to secure and trustworthy media annotation
No full textMedia assets can easily be manipulated with photo editing software or artificially created using deep learning techniques. This can be done with the intention to mislead, but also for creative or educational purposes. Clear annotation of media modifications is a crucial element to assess trustworthiness. However, these annotations should be attached securly to prevent them from being compromised. In addition, to achieve a wide adoption, interoperability is essential. This paper gives an overview of the media manipulation history, discusses the state-of-the-art and challenges related to AI-based detection methods. The paper then introduces JPEG Fake Media as a provenance-based sustainable approach to secure and trustworthy media annotation. JPEG Fake Media has the objective to produce a standard that can facilitate secure and reliable annotation of media asset creation and modifications. The standard shall support good faith usage scenarios as well as those with malicious intent
Sustainable small-scale marine fishing resources and communities in Kerala, India: key findings and recommendations
No full textEmbedded vision systems: A review of the literature
No full textOver the past two decades, the use of low power Field Programmable Gate Arrays (FPGA) for the acceleration of various vision systems mainly on embedded devices have become widespread. The reconfigurable and parallel nature
of the FPGA opens up new opportunities to speed-up computationally intensive vision and neural algorithms on embedded and portable devices. This paper presents a comprehensive review of embedded vision algorithms and applications over the past decade. The review will discuss vision based systems and approaches, and how they have been implemented on embedded devices. Topics covered include image acquisition, preprocessing, object detection and tracking, recognition as well as high-level classification. This is followed by an outline of
the advantages and disadvantages of the various embedded implementations. Finally, an overview of the challenges in the field and future research trends are presented. This review is expected to serve as a tutorial and reference source for embedded computer vision systems
The multimedia blockchain: a distributed and tamper-proof media transaction framework
No full textA distributed and tamper proof media transaction framework is proposed based on the blockchain model. Current multimedia distribution does not preserve self-retrievable information of transaction trails or content modification histories. For example, digital copies of valuable artworks, creative media and entertainment contents are distributed for various purposes including exhibitions, gallery collections or in media production
workflow. Original media is often edited for creative content preparation or tampered with to fabricate false propaganda over social media. However there is no existing trusted mechanism that can easily retrieve either the transaction trails or the modification histories. We propose a novel watermarking based Multimedia Blockchain framework that can address such
issues. The unique watermark information contains two pieces of information: a) a cryptographic hash that contains transaction histories (blockchain transactions log) and b) an image hash that preserves retrievable original media content. Once the watermark is extracted, first part of the watermark is passed to a distributed
ledger to retrieve the historical transaction trail and the latter part is used to identify the edited / tampered regions. The paper outlines the requirements, the challenges and demonstrates the proof of this concept
On robustness against JPEG2000: a performance evaluation of wavelet-based watermarking techniques
No full textWith the emergence of new scalable coding standards, such as JPEG2000, multimedia is stored as scalable coded bit streams that may be adapted to cater network, device and usage preferences in multimedia usage chains providing universal multimedia access. These adaptations include quality, resolution, frame rate and region of interest scalability and achieved by discarding least significant parts of the bit stream according to the scalability criteria. Such content adaptations may also affect the content protection data, such as watermarks, hidden in the original content. Many wavelet-based robust watermarking techniques robust to such JPEG2000 compression attacks are proposed in the literature. In this paper, we have categorized and evaluated the robustness of such wavelet-based image watermarking techniques against JPEG2000 compression, in terms of algorithmic choices, wavelet kernel selection, subband selection, or watermark selection using a new modular framework. As most of the algorithms use a different set of parametric combination, this analysis is particularly useful to understand the effect of various parameters on the robustness under a common platform and helpful to design any such new algorithm. The analysis also considers the imperceptibility performance of the watermark embedding, as robustness and imperceptibility are two main watermarking properties, complementary to each other
Statistical t+2D subband modelling for crowd counting
No full textCounting people automatically in a crowded scenario is important to assess safety and to determine behaviour in surveillance operations. In this paper we propose a new algorithm using the statistics of the spatio-temporal wavelet subbands. A t+2D lifting based wavelet transform is exploited to generate a motion saliency map which is then used to extract novel parametric statical texture features. We compare our approach to existing crowd counting approaches and show improvement on standard benchmark sequences, demonstrating the robustness of the extracted features
Domain-Specific Optimisations for Image Processing on FPGAs
No full textImage processing algorithms on FPGAs have increasingly become more pervasive in real-time vision applications. Such algorithms are computationally complex and memory intensive, which can be severely limited by available hardware resources. Optimisations are therefore necessary to achieve better performance and efficiency. We hypothesise that, unlike generic computing optimisations, domain-specific image processing optimisations can improve performance significantly. In this paper, we propose three domain-specific optimisation strategies that can be applied to many image processing algorithms. The optimisations are tested on popular image-processing algorithms and convolution neural networks on CPU/GPU/FPGA and the impact on performance, accuracy and power are measured. Experimental results show major improvements over the baseline non-optimised versions for both convolution neural networks (MobileNetV2 & ResNet50), Scale-Invariant Feature Transform (SIFT) and filter algorithms. Additionally, the optimised FPGA version of SIFT significantly outperformed an optimised GPU implementation when energy consumption statistics are taken into account
- …
