Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

This document provides updates to IEEE Std 802.16's MIB for the MAC, PHY and asso- ciated management procedures in order to accommodate recent extensions to the standard.

IEEE Standard for Local and Metropolitan Area Networks Part 16: Air Interface for Fixed Broadband Wireless Access Systems Draft Amendment: Management Information Base Extensions

A forward-facing vision system for a vehicle includes a forward-facing camera disposed in a windshield electronics module attached at a windshield of the vehicle and viewing through the windshield. A control includes a processor that, responsive to processing of captured image data, detects taillights of leading vehicles during nighttime conditions and, responsive to processing of captured image data, detects lane markers on a road being traveled by the vehicle. The control, responsive to lane marker detection and a determination that the vehicle is drifting out of a traffic lane, may control a steering system of the vehicle to mitigate such drifting, with the steering system manually controllable by a driver of the vehicle irrespective of control by the control. The processor, based at least in part on detection of lane markers via processing of captured image data, determines curvature of the road being traveled by the vehicle.

Vision system for vehicle

A vehicular vision system includes a camera having a lens and a CMOS photosensor array having a plurality of photosensor elements. The camera is disposed at an interior portion of a vehicle equipped with the vehicular vision system. The camera one of (i) views exterior of the equipped vehicle through the windshield of the equipped vehicle and forward of the equipped vehicle and (ii) views from the windshield of the equipped vehicle into the interior cabin of the equipped vehicle. A control includes an image processor that processes image data captured by the photosensor array. The image processor processes captured image data to detect an object viewed by the camera. The photosensor array is operable at a plurality of exposure periods and at least one exposure period of the plurality of exposure periods is dynamically variable.

Vehicular vision system

A driver assistance system for a vehicle includes an imaging device having a field of view forward of a vehicle and in a direction of travel of the equipped vehicle, an image processor operable to process image data captured by the imaging device, and a global positioning system operable to determine a geographical location of the vehicle. The equipped vehicle includes an adaptive speed control system for controlling the speed of the equipped vehicle. The adaptive speed control system may reduce the speed of the equipped vehicle responsive at least in part to a detection of a curve in the road ahead of the equipped vehicle via processing by the image processor of image data captured by the imaging device.

Driver assistance system for vehicle

We investigate the scenario of using the automatic repeat request (ARQ) retransmission scheme for two-way video communications over wireless Rayleigh fading channels. Video quality is the major concern of these applications. We show that, during the retransmissions of error packets, due to the reduced channel throughput, the video encoder buffer may fill-up quickly and cause the TMN8 rate-control algorithm to significantly reduce the bits allocated to each video frame. This results in PSNR degradation and many skipped frames. To minimize the number of frames skipped, we propose improved rate-control schemes that take into consideration the effects of the video buffer fill-up, an a priori channel model, and the channel feedback information. We also show that a discrete cosine transform (DCT) coefficient soft-thresholding scheme can be applied to further improve video quality. As a result, our proposed rate-control schemes encode the video sequences with less frame skipping and with higher PSNR compared to TMN8.

A rate-control scheme for video transport over wireless channels

We consider the scenario of using Automatic Repeat reQuest (ARQ) retransmission for two-way low-bit-rate video communications over wireless Rayleigh fading channels. Low-delay constraint may require that a corrupted retransmitted packet not be retransmitted again, and thus there will be packet errors at the decoder which results in video quality degradation. We propose a scheme to improve the video quality. First, we propose a low-delay interleaving scheme that uses the video encoder buffer as a part of interleaving memory. Second, we propose a conditional retransmission strategy that reduces the number of retransmissions. Simulation results show that our proposed scheme can effectively reduce the number of packet errors and improve the channel utilization. As a result, we reduce the number of skipped frames and obtain a peak signal-to-noise ratio improvement up to about 4 dB compared to H.263 TMN-8.

/pdf/wireless-video-transport-using-conditional-retransmission-202tzb2x21.pdf

Wireless video transport using conditional retransmission and low-delay interleaving

Anomaly detection is of great significance for intelligent surveillance videos. Current works typically struggle with object detection and localization problems due to crowded and complex scenes. Hence, we propose a Deep Spatiotemporal Translation Network (DSTN), novel unsupervised anomaly detection and localization method based on Generative Adversarial Network (GAN) and Edge Wrapping ( $EW$ ). In training, we use only the frames of normal events in order to generate their corresponding dense optical flow as temporal features. During testing, since all the video sequences are input into the system, unknown events are considered as anomalous events due to the fact that the model knows only the normal patterns. To benefit from the information provided by both appearance and motion features, we introduce (i) a novel fusion of background removal and real optical flow frames with (ii) a concatenation of the original and background removal frames. We improve the performance of anomaly localization in the pixel-level evaluation by proposing (iii) the Edge Wrapping to reduce the noise and suppress non-related edges of abnormal objects. Our DSTN has been tested on publicly available anomaly datasets, including UCSD pedestrian, UMN, and CUHK Avenue. The results show that it outperforms other state-of-the-art algorithms with respect to the frame-level evaluation, the pixel-level evaluation, and the time complexity for abnormal object detection and localization tasks.

/pdf/unsupervised-anomaly-detection-and-localization-based-on-48iqvvddxe.pdf

Unsupervised Anomaly Detection and Localization Based on Deep Spatiotemporal Translation Network

The paper presents a statistical adaptive realtime background subtraction algorithm that is very robust to moving shadows and dynamic scene environment The algorithm enhances the previously developed method reported by T Horprascrt et al (see Proc IEEE ICCV'99 Frame-rate Workshop, 1999) by adding adaptation of the model corresponding to a dynamic background using adaptive brightness and color distortion In addition, we propose a novel "vivacity factor" to measure the activities of foreground objects It is used to delay the adaptation rate for the area of often-occurring moving foregrounds Our method provides a solution to real-time moving object and shadow detection in the dynamic background scene of a video stream We also develop the learning-rate control mechanism that is not addressed by most background subtraction algorithms

An adaptive real-time background subtraction and moving shadows detection

Face recognition can be used in several applications such as in surveillance, identification in login system and personalized technology. Recognizing multiple face in realtime on the embedded system is very challenging due to the complexity computation of the processing. In this paper, we propose multiple face recognition framework which is implemented on the embedded GPU system. The framework contains face detection based on convolutional neural network (CNN) with face tracking and state of the art deep CNN face recognition algorithm. We implemented the proposed framework into the embedded GPU system, i.e., NVIDIA Jetson TX2 board. Experimental results showed that the proposed system can recognize multiple faces up to 8 faces at the same time in real time with up to 0.23 seconds of processing time and with the minimum recognition rate above 83.67%.

Supavadee Aramvith

Papers

A rate-control scheme for video transport over wireless channels

Wireless video transport using conditional retransmission and low-delay interleaving

Unsupervised Anomaly Detection and Localization Based on Deep Spatiotemporal Translation Network

An adaptive real-time background subtraction and moving shadows detection

Real-Time Multiple Face Recognition using Deep Learning on Embedded GPU System