Chih-Wei Huang

Discovery and fusion of salient multimodal features toward news story segmentation

In this paper, we present our new results in news video story segmentation and classification in the context of TRECVID video retrieval benchmarking event 2003. We applied and extended the Maximum Entropy statistical model to effectively fuse diverse features from multiple levels and modalities, including visual, audio, and text. We have included various features such as motion, face, music/speech types, prosody, and high-level text segmentation information. The statistical fusion model is used to automatically discover relevant features contributing to the detection of story boundaries. One novel aspect of our method is the use of a feature wrapper to address different types of features -- asynchronous, discrete, continuous and delta ones. We also developed several novel features related to prosody. Using the large news video set from the TRECVID 2003 benchmark, we demonstrate satisfactory performance (F1 measures up to 0.76 in ABC news and 0.73 in CNN news), present how these multi-level multi-modal features construct the probabilistic framework, and more importantly observe an interesting opportunity for further improvement.

OLM: Opportunistic Layered Multicasting for Scalable IPTV over Mobile WiMAX

We propose Opportunistic Layered Multicasting (OLM), a joint user scheduling and resource allocation algorithm that provides enhanced quality and efficiency for layered video multicast over Mobile WiMAX. This work is a lead off and complete synergy of layered video multicasting with opportunistic concept. The target application is characterized by groups of users acquiring popular video programs over a fading channel. To accommodate various bandwidth requirements and device capability, video streams are coded into base and enhancement layers using scalable video coding technology. Correspondingly, the optimization problems, which select the best subset of users to receive a specific video layer and assign the most appropriate modulation and coding scheme for this video layer, are specifically formulated for both video layer types. We also design fast and effective algorithms to bridge the gap between theoretical throughput capacity and implementation concerns. Thus, the basic video quality can be efficiently guaranteed to all subscribers while creating most utility out of limited resources on enhancement information. To overcome the inevitable packet loss in a multicast session, an FEC rate adaptation scheme to approach theoretical performance is also presented. Favorable performance of the proposed algorithms is demonstrated by simulations utilizing realistic Mobile WiMAX parameters.

News video story segmentation using fusion of multi-level multi-modal features in TRECVID 2003

We present our new results in news video story segmentation and classification in the context of the TRECVID video retrieval benchmarking event 2003. We applied and extended the maximum entropy statistical model to fuse diverse features effectively from multiple levels and modalities, including visual, audio, and text. We have included various features such as motion, face, music/speech types, prosody, and high-level text segmentation information. The statistical fusion model is used to discover automatically relevant features contributing to the detection of story boundaries. One novel aspect of our method is the use of a feature wrapper to address different types of features - asynchronous, discrete, continuous and delta ones. We also developed several novel features related to prosody. Using the large news video set from the TRECVID 2003 benchmark, we demonstrate satisfactory performance (F1 measure up to 0.76) and, more importantly, observe an interesting opportunity for further improvement.

Advanced formation and delivery of traffic information in intelligent transportation systems

To meet the safety requirement for the increasing traffic densities nowadays, there exists a growing demand for advanced systems that can provide drivers essential traffic and travel information to improve road safety and traffic efficiency. In this paper, we combine the video analysis and multimedia networking technologies to present a highly integrated intelligent system that can achieve the above goals. For traffic information, the system presented in this paper collects traffic parameters and detects relevant events by analyzing traffic surveillance videos. Through robust tracking algorithms and reasoning logics, important traffic parameters and events are extracted from the surveillance videos accurately. Afterwards, summarized real-time traffic conditions and important events along with corresponding live traffic videos are formed into layers and multicasted through an integration of WiMAX infrastructure and vehicular ad hoc networks (VANET). By the support of adaptive modulation and coding in WiMAX, the radio resources can be optimally allocated when performing multicast so as to dynamically adjust the number of data layers received by users. In addition to multicast supported by WiMAX, we also design a knowledge propagation and information relay scheme by VANET. Through this relaying technology, about 80% of the mobile stations that were unable to subscribe additional layers of data due to insufficient downlink bandwidth from WiMAX could regain more than 90% of the data in the additional layers within tolerable buffering time.

An Energy-Efficient and Delay-Aware Wireless Computing System for Industrial Wireless Sensor Networks

Industrial wireless sensor networks have attracted much attention as a cornerstone to making the smart factories real. Utilizing industrial wireless sensor networks as a base for smart factories makes it possible to optimize the production line without human resources, since it provides industrial Internet of Things service, where various types of data are collected from sensors and mined to control the machines based on the analysis result. On the other hand, a fog computing node, which executes such real-time feedback control, should be capable of real-time data collection, management, and processing. To achieve these requirements, in this paper, we introduce wireless computing system (WCS) as a fog computing node. Since there are a lot of servers and each server has 60 GHz antennas to connect to other servers and sensors, WCS has high collecting and processing capabilities. However, in order to fulfill a demand for real-time feedback control, WCS needs to satisfy an acceptable delay for data collection. In addition, lower power consumption is required in order to reduce the cost for the factory operation. Therefore, we propose an energy-efficient and delay-aware WCS. Since there is a tradeoff relationship between the power consumption and the delay for data collection, our proposed system controls the sleep schedule and the number of links to minimize the power consumption while satisfying an acceptable delay constraint. Furthermore, the effectiveness of our proposed system is evaluated through extensive computer simulations.

Layered Video Resource Allocation in Mobile WiMAX Using Opportunistic Multicasting

We propose a resource allocation algorithm that provides enhanced QoS and efficiency for layered video multicast over Mobile WiMAX. The application is characterized by groups of users acquiring popular video programs over a fading channel. To accommodate various bandwidth requirements and adaptive perceptual quality to different users, video streams are coded into base and enhancement layers using scalable video coding technology. Correspondingly, the optimization problems, which assign the most appropriate modulation schemes to provide best video quality to as many users, can be formulated using opportunistic multicasting concept. We maximize the minimum effective throughput across all users for mandatory (base) layer delivery through adapting modulation and coding schemes. At the same time, optional (enhancement) layers are allocated to maximize total utility. Thus the basic video quality can be efficiently guaranteed to all subscribers while making most out of limited resources on enhancement information. We further present an FEC rate adaptation scheme to approach theoretical performance. Favorable performance of the proposed algorithms is demonstrated by simulations utilizing realistic Mobile WiMAX parameters.

Airtime Fair Distributed Cross-Layer Congestion Control for Real-Time Video Over WLAN

We propose a distributed cross-layer congestion control algorithm that provides enhanced quality of service QoS and reliable operation for real-time uplink video over WiFi applications. Such applications are characterized by many wireless devices transmitting video at various PHY rates over a relatively congested channel. Unfortunately, todays off-the-shelf 802.11 equipment can be easily demonstrated to suffer catastrophic failure when subject to these conditions-let alone provide acceptable perceptual quality to the user. We show that in order to remedy these issues, it is preferable to apply airtime fairness with a cross-layer approach. The idea is to use a fast frame-by-frame control loop in the carrier sense multiple access/collision avoidance (CSMA/CA)-based medium access control (MAC) layer while simultaneously exploiting the powerful control loop gain attainable by performing source-rate adaptation in the application layer. We support the proposed algorithm through both simulation and experimentation with various channel and PHY rate scenarios.

An Embedded Packet Train and Adaptive FEC Scheme for VoIP Over Wired/Wireless Ip Networks

Voice over IP (VoIP) has become the fastest growing wireless alternative to conventional telephony service by way of ongoing deployment of WLAN hotspots and even powerful WiMAX coverage. Resulting from the wired/wireless combined best-effort based heterogeneous IP networks which provide more fluctuation in available bandwidth and end-to-end delay, the performance of VoIP quality, especially using the handheld wireless devices, has been greatly degraded due to frequent packet loss and longer delays. This paper proposes a real-time embedded packet train probing scheme for estimating end-to-end available bandwidth so as to accomplish effective congestion control. By trading acceptable delays with adaptive packetization of voice bitstreams, as well as adaptive insertion of forward error correction (FEC) packets, an optimized system driven QoS approach for VoIP can thus be achieved

Reliable Multimedia Broadcasting over Dense Wireless Ad-Hoc Networks (Invited Paper)

Broadcasting is an essential operation for Wireless Ad Hoc Networks to perform routing path discovery, and it has become the predominant technology for message dissemination in Vehicular Ad Hoc Networks (VANETs). In the reactive routing schemes of wireless ad hoc network, Routing Request (RREQ) packets are broadcast from the source, and once received the destination traces back the broadcasting path to build an on-demand route. In VANETs, different broadcasting schemes have been proposed for safety, comfort, and commercial applications. However, broadcasting usually generates a lot of redundant messages which would cause excessive channel contention and packet collisions, especially when the density of the network becomes higher. In this survey article, we first introduce the most common data dissemination techniques used in wireless ad hoc networks. After that, we discuss techniques that have been proposed to mitigate the broadcast storm problem. Finally, we introduce an effective model for analyzing the broadcasting schemes, and based on the model we propose an adaptively adjusted probabilistic scheme that highly improves the reliability of broadcasting in dense ad hoc networks.

Link Layer Packet Loss Classification for Link Adaptation in WLAN

Voice over IP (VoIP) and high quality video streaming becomes an alternative to conventional telephony and TV service in many locations by way of ongoing deployment of WLAN hotspots. The newly proved IEEE 802.11e QoS enhancement standard will be a proper solution of delay demanding for real-time multimedia applications, while the existing auto rate fallback (ARF) link adaptation scheme, designed to improve wireless transmission by dynamically selecting transmission rates and frame sizes, cannot effectively solve the QoS concerns of multimedia communication due to the growing UDP traffic. In this paper, we presented comprehensive analyses of link layer behavior to infer the cause of packet loss in a WLAN. More specifically, we classify the packet loss into either congestion or wireless errors based mainly on delays and MAC layer parameters under congestion and/or link error dominated status. A link layer packet loss classification scheme can thus be proposed to support link adaptation for VoIP applications in WLAN.