“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

Automatic video analysis from urban surveillance cameras is a fast-emerging field based on computer vision techniques. We present here a comprehensive review of the state-of-the-art computer vision for traffic video with a critical analysis and an outlook to future research directions. This field is of increasing relevance for intelligent transport systems (ITSs). The decreasing hardware cost and, therefore, the increasing deployment of cameras have opened a wide application field for video analytics. Several monitoring objectives such as congestion, traffic rule violation, and vehicle interaction can be targeted using cameras that were typically originally installed for human operators. Systems for the detection and classification of vehicles on highways have successfully been using classical visual surveillance techniques such as background estimation and motion tracking for some time. The urban domain is more challenging with respect to traffic density, lower camera angles that lead to a high degree of occlusion, and the variety of road users. Methods from object categorization and 3-D modeling have inspired more advanced techniques to tackle these challenges. There is no commonly used data set or benchmark challenge, which makes the direct comparison of the proposed algorithms difficult. In addition, evaluation under challenging weather conditions (e.g., rain, fog, and darkness) would be desirable but is rarely performed. Future work should be directed toward robust combined detectors and classifiers for all road users, with a focus on realistic conditions during evaluation.

A Review of Computer Vision Techniques for the Analysis of Urban Traffic

Over the past decade, vision-based vehicle detection techniques for road safety improvement have gained an increasing amount of attention. Unfortunately, the techniques suffer from robustness due to huge variability in vehicle shape (particularly for motorcycles), cluttered environment, various illumination conditions, and driving behavior. In this paper, we provide a comprehensive survey in a systematic approach about the state-of-the-art on-road vision-based vehicle detection and tracking systems for collision avoidance systems (CASs). This paper is structured based on a vehicle detection processes starting from sensor selection to vehicle detection and tracking. Techniques in each process/step are reviewed and analyzed individually. Two main contributions in this paper are the following: survey on motorcycle detection techniques and the sensor comparison in terms of cost and range parameters. Finally, the survey provides an optimal choice with a low cost and reliable CAS design in vehicle industries.

Vehicle Detection Techniques for Collision Avoidance Systems: A Review

This paper presents a system for vehicle detection, tracking and classification from roadside CCTV. The system counts vehicles and separates them into four categories: car, van, bus and motorcycle (including bicycles). A new background Gaussian Mixture Model (GMM) and shadow removal method have been used to deal with sudden illumination changes and camera vibration. A Kalman filter tracks a vehicle to enable classification by majority voting over several consecutive frames, and a level set method has been used to refine the foreground blob. Extensive experiments with real world data have been undertaken to evaluate system performance. The best performance results from training a SVM (Support Vector Machine) using a combination of a vehicle silhouette and intensity-based pyramid HOG features extracted following background subtraction, classifying foreground blobs with majority voting. The evaluation results from the videos are encouraging: for a detection rate of 96.39%, the false positive rate is only 1.36% and false negative rate 4.97%. Even including challenging weather conditions, classification accuracy is 94.69%.

Vehicle detection, tracking and classification in urban traffic

A two-fold transformation model for human action recognition using decisive pose

Generative adversarial networks (GANs) have been increasingly used as feature mapping functions in speech enhancement, in which the noisy speech features are transformed to the clean ones through the generators. This article proposes a novel speech enhancement model based on a cycle-consistent relativistic GAN with Dilated Residual Networks and a Multi-attention mechanism. Using the adversarial loss, improved cycle-consistency losses, and an identity-mapping loss, a noisy-to-clean generator $G$ and an inverse clean-to-noisy generator $F$ simultaneously learn the forward and backward mappings between the source and target domains. To guarantee the stability of the training process, we replace vanilla GAN loss with relativistic average GAN loss and use spectral normalization in discriminators so that they conform to Lipschitz continuity. Furthermore, we employ two attention-based components as multi-attention mechanism to reduce importing signal distortion: attention U-net gates and dilated residual self-attention blocks. By employing these components, our proposed generators can capture long-term inner dependencies between elements of speech features and further preserve linguistic information. Experimental results on a public dataset indicate that the proposed model achieves state-of-the-art speech enhancement performance, especially in reducing speech distortion and improving signal overall quality. Compared with the representative GAN-based approaches, the proposed method significantly achieves the best performance in terms of STOI, CSIG, COVL, and CBAK objective metrics. Moreover, we demonstrate the contribution of each proposed component including relativistic average loss, attention U-net gate, self-attention layers, spectral normalization, and dilation operation by ten comparison systems.

/pdf/improved-relativistic-cycle-consistent-gan-with-dilated-3tmcqo7o5a.pdf

Improved Relativistic Cycle-Consistent GAN With Dilated Residual Network and Multi-Attention for Speech Enhancement

Multiple objects tracking is an important and challenging issue, because of difficulties caused by variable number of objects and interaction of objects. In this paper, we present a distributed tracking approach based on Bayesian framework to avoid huge computational expenses involved in sampling from a joint state space. Single-object trackers easily suffer from false identities of objects after severe occlusions because of hidden first-order Markov hypotheses. To solve the problem, we define a transition matrix between consecutive frames to denote the occurrences and probabilities of dynamic events, such as continuation, appearance, disappearance, interaction and split associating current object detections and previous tracking results. Analyzing transition probabilities combined with position, direction and appearance, we can infer depth ordering of occlusions.The transition matrix is able to effectively guide multiple single-object particle filters to predict and update the state of objects. The simulations demonstrate that the proposed approach can initialize automatically and track varying number of objects with occlusions.

An Efficient Multi-object Tracking Method Using Multiple Particle Filters

A novel and efficient human action recognition method utilizing spatio-temporal interest point detector and 3D speed up robust features (3D SURF) descriptor is proposed. The spatio-temporal interest points are detected using two separate linear filters. Then 3D SURF descriptor is presented and demonstrated in detail to represent the local region around interest point. The experimental results on KTH and Weizmann dataset prove that the proposed method is superior to similar methods. Especially, compared with the popular 3DSIFT, 3D SURF is advantage in recognition rate and lower computation cost as well.

Human action recognition using spatio-temoporal descriptor

Dynamic textures (or temporal textures) are a kind of visual motion pattern, and their dynamics are not trackable. Dynamic textures such as flames, smoke, and water are statistical stationary and exhibit spatial self-similarity and temporal self-similarity. Recently, description of dynamic textures has attracted growing attention. In this paper, a novel method for analyzing and synthesizing dynamic textures is proposed. First, the dynamic textures are modeled by combination of dynamic texture units. Second, the segment parameters and dynamic texture units' parameters are learnt at the same time. To reduce computational complexity, we discard Fourier coefficients that are under contribution ratio threshold. Our algorithm is general and automatic, and it works well on various types of textures. Experimental results demonstrate that our approach can reconstruct dynamic texture sequences with promising visual quality and fewer coefficients.

A Novel Method of Dynamic Textures Analysis and Synthesis

Existing news recommendation methods suffer from sparse and weak interaction data, leading to reduced effectiveness and explainability. Knowledge reasoning, which explores inferential trajectories in the knowledge graph, can alleviate data sparsity and provide explicitly recommended explanations. However, brute-force pre-processing approaches used in conventional methods are not suitable for fast-changing news recommendation. Therefore, we propose an explainable news recommendation model: the Reinforced and Contrastive Heterogeneous Network Reasoning Model for Explainable News Recommendation (RCENR), consisting of NHN-R2 and MR&CO frameworks. The NHN-R2 framework generates user/news subgraphs to enhance recommendation and extend the dimensions and diversity of reasoning. The MR&CO framework incorporates contrastive learning with a reinforcement-based strategy for self-supervised and efficient model training. Experiments on the MIND dataset show that RCENR is able to improve recommendation accuracy and provide diverse and credible explanations.

RCENR: A Reinforced and Contrastive Heterogeneous Network Reasoning Model for Explainable News Recommendation

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Jingling Wang

Author Tools

Chat about Author