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

In the era of the Internet of Things (IoT), an enormous amount of sensing devices collect and/or generate various sensory data over time for a wide range of fields and applications. Based on the nature of the application, these devices will result in big or fast/real-time data streams. Applying analytics over such data streams to discover new information, predict future insights, and make control decisions is a crucial process that makes IoT a worthy paradigm for businesses and a quality-of-life improving technology. In this paper, we provide a thorough overview on using a class of advanced machine learning techniques, namely deep learning (DL), to facilitate the analytics and learning in the IoT domain. We start by articulating IoT data characteristics and identifying two major treatments for IoT data from a machine learning perspective, namely IoT big data analytics and IoT streaming data analytics. We also discuss why DL is a promising approach to achieve the desired analytics in these types of data and applications. The potential of using emerging DL techniques for IoT data analytics are then discussed, and its promises and challenges are introduced. We present a comprehensive background on different DL architectures and algorithms. We also analyze and summarize major reported research attempts that leveraged DL in the IoT domain. The smart IoT devices that have incorporated DL in their intelligence background are also discussed. DL implementation approaches on the fog and cloud centers in support of IoT applications are also surveyed. Finally, we shed light on some challenges and potential directions for future research. At the end of each section, we highlight the lessons learned based on our experiments and review of the recent literature.

Deep Learning for IoT Big Data and Streaming Analytics: A Survey

2017 25th European Signal Processing Conference (EUSIPCO)

Rotation detection is a challenging task due to the difficulties of locating the multi-angle objects and separating them effectively from the background. Though considerable progress has been made, for practical settings, there still exist challenges for rotating objects with large aspect ratio, dense distribution and category extremely imbalance. In this paper, we propose an end-to-end refined single-stage rotation detector for fast and accurate object detection by using a progressive regression approach from coarse to fine granularity. Considering the shortcoming of feature misalignment in existing refined single-stage detector, we design a feature refinement module to improve detection performance by getting more accurate features. The key idea of feature refinement module is to re-encode the position information of the current refined bounding box to the corresponding feature points through pixel-wise feature interpolation to realize feature reconstruction and alignment. For more accurate rotation estimation, an approximate SkewIoU loss is proposed to solve the problem that the calculation of SkewIoU is not derivable. Experiments on three popular remote sensing public datasets DOTA, HRSC2016, UCAS-AOD as well as one scene text dataset ICDAR2015 show the effectiveness of our approach. Tensorflow and Pytorch version codes are available at this https URL and this https URL, and R3Det is also integrated in our open source rotation detection benchmark: this https URL.

R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object

Arbitrary-oriented object detection has recently attracted increasing attention in vision for their importance in aerial imagery, scene text, and face etc. In this paper, we show that existing regression-based rotation detectors suffer the problem of discontinuous boundaries, which is directly caused by angular periodicity or corner ordering. By a careful study, we find the root cause is that the ideal predictions are beyond the defined range. We design a new rotation detection baseline, to address the boundary problem by transforming angular prediction from a regression problem to a classification task with little accuracy loss, whereby high-precision angle classification is devised in contrast to previous works using coarse-granularity in rotation detection. We also propose a circular smooth label (CSL) technique to handle the periodicity of the angle and increase the error tolerance to adjacent angles. We further introduce four window functions in CSL and explore the effect of different window radius sizes on detection performance. Extensive experiments and visual analysis on two large-scale public datasets for aerial images i.e. DOTA, HRSC2016, as well as scene text dataset ICDAR2015 and MLT, show the effectiveness of our approach. The code is public available at https://github.com/Thinklab-SJTU/CSL_RetinaNet_Tensorflow.

Arbitrary-Oriented Object Detection with Circular Smooth Label

https://eprints.ncl.ac.uk/file_store/production/211465/D57F91E3-2C01-4630-B750-3DB787FD7C9A.pdf

An unsupervised acoustic fall detection system using source separation for sound interference suppression

An enhanced sequential Monte Carlo probability hypothesis density (PHD) filter-based multiple human tracking system is presented. The proposed system mainly exploits two concepts: a novel adaptive gating technique and an online group-structured dictionary learning strategy. Conventional PHD filtering methods preset the target birth intensity and the gating threshold for selecting real observations for the PHD update. This often yields inefficiency in false positives and missed detections in a cluttered environment. To address this issue, a measurement-driven mechanism based on a novel adaptive gating method is proposed to adaptively update the gating sizes. This yields an accurate approach to discriminate between survival and residual measurements by reducing the clutter inferences. In addition, online group-structured dictionary learning with a maximum voting method is used to robustly estimate the target birth intensity. It enables the new-born targets to be automatically detected from noisy sensor measurements. To improve the adaptability of our group-structured dictionary to appearance and illumination changes, we employ the simultaneous code word optimization algorithm for the dictionary update stage. Experimental results demonstrate our proposed method achieves the best performance amongst state-of-the-art random finite set-based methods, and the second best online tracker ranked on the leaderboard of latest MOT17 challenge.

/pdf/particle-phd-filter-based-multiple-human-tracking-using-3akhdticcq.pdf

Particle PHD Filter Based Multiple Human Tracking Using Online Group-Structured Dictionary Learning

Object detection in aerial images is a challenging task due to the lack of visible features and variant orientation of objects. Significant progress has been made recently for predicting targets from aerial images with horizontal bounding boxes (HBBs) and oriented bounding boxes (OBBs) using two-stage detectors with region based convolutional neural networks (R-CNN), involving object localization in one stage and object classification in the other. However, the computational complexity in two-stage detectors is often high, especially for orientational object detection, due to anchor matching and using regions of interest (RoI) pooling for feature extraction. In this paper, we propose a one-stage anchor free detector for orientational object detection, namely, an interactive embranchment network (IENet), which is built upon a detector with prediction in per-pixel fashion. First, a novel geometric transformation is employed to better represent the oriented object in angle prediction, then a branch interactive module with a self-attention mechanism is developed to fuse features from classification and box regression branches. Finally, we introduce an enhanced intersection over union (IoU) loss for OBB detection, which is computationally more efficient than regular polygon IoU. Experiments conducted demonstrate the effectiveness and the superiority of our proposed method, as compared with state-of-the-art detectors.

IENet: Interacting Embranchment One Stage Anchor Free Detector for Orientation Aerial Object Detection.

Video-based multiple human tracking often involves several challenges, including target number variation, object occlusions, and noise corruption in sensor measurements. In this paper, we propose a novel method to address these challenges based on probability hypothesis density (PHD) filtering with a Markov chain Monte Carlo (MCMC) implementation. More specifically, a novel social force model (SFM) for describing the interaction between the targets is used to calculate the likelihood within the MCMC resampling step in the prediction step of the PHD filter, and a one class support vector machine (OCSVM) is then used in the update step to mitigate the noise in the measurements, where the SVM is trained with features from both color and oriented gradient histograms. The proposed method is evaluated and compared with state-of-the-art techniques using sequences from the CAVIAR, TUD, and PETS2009 datasets based on the mean Euclidean tracking error on each frame, the optimal subpattern assignment metric, and the multiple object tracking precision metric. The results show improved performance of the proposed method over the baseline algorithms, including the traditional particle PHD filtering method, the traditional SFM-based particle filtering method, multi-Bernoulli filtering, and an online-learning-based tracking method.

/pdf/social-force-model-based-mcmc-ocsvm-particle-phd-filter-for-1ik2075bun.pdf

Social Force Model-Based MCMC-OCSVM Particle PHD Filter for Multiple Human Tracking

We propose a novel computer vision based fall detection system using deep learning methods to analyse the postures in a smart home environment for detecting fall activities. Firstly, background subtraction is employed to extract the foreground human body. Then the binary human body images form the input to the classifier. Two deep learning approaches based on a Boltzmann machine and deep belief network are compared with a support vector machine approach. The final decision on the occurrence of a fall is made on the basis of combining the classifier output with certain contextual rules. Evaluations are performed on recordings from a real home care environment, in which 15 people create 2904 postures.

Pengming Feng

Papers

An unsupervised acoustic fall detection system using source separation for sound interference suppression

Particle PHD Filter Based Multiple Human Tracking Using Online Group-Structured Dictionary Learning

IENet: Interacting Embranchment One Stage Anchor Free Detector for Orientation Aerial Object Detection.

Social Force Model-Based MCMC-OCSVM Particle PHD Filter for Multiple Human Tracking

Deep learning for posture analysis in fall detection