Intelligent Video Ingestion for Real-time Traffic Monitoring

Abstract

As an indispensable part of modern critical infrastructures, cameras deployed at strategic places and prime junctions in an intelligent transportation system (ITS), can help operators in observing traffic flow, identifying any emergency situation, or making decisions regarding road congestion without arriving on the scene. However, these cameras are usually equipped with heterogeneous and turbulent networks, making the real-time smooth playback of traffic monitoring videos with high quality a grand challenge. In this paper, we propose a light-weight Deep Reinforcement Learning (DRL) based approach, namely sRC-C (smart bitRate Control with a Continuous action space), to enhance the quality of realtime traffic monitoring by adjusting the video bitrate adaptively. Distinguished from the existing bitrate adjusting approaches, sRC-C can overcome the bias incurred by deterministic discretization of candidate bitrates by adjusting the video bitrate with more fine-grained control from a continuous action space, thus significantly improving the Quality-of-Service (QoS). With carefully designed state space and neural network model, sRC-C can be implemented on cameras with scarce resources to support real-time live video streaming with low inference time. Extensive experiments show that sRC-C can reduce the frame loss counts and hold time by 24% and 15.5%, respectively, even with comparable bandwidth utilization. Meanwhile, compared to the-state-of-art approaches, sRC-C can improve the QoS by 30.4%.

Efficient Visual Computing With Camera RAW Snapshots

“…The lossless decoding of x i , i ∈ [1,4] is organized as: 1) The x i is dyadically upsampled from x i−1 with 2× scaling at each dimension, i.e., each pixel in x i−1 is expanded to four pixels arranged in a local 2×2 patch in x i ; 2) As in Fig. 5b, the upper-left pixel of each 2×2 patch of x i is directly filled using the corresponding pixel of x i−1 (highlighted with red box), while the other three pixels in each 2×2 patch of x i is decoded using the conditional probability of logistic distribution that is characterized by the Z i ; Note that a special case is made for the processing of x 0 since there are no available pixels from a lower resolution scale.…”

“…C ONVENTIONAL cameras capture visual information in a scene and present it in the RGB (or equivalent YCbCr) format for subsequent visual computing (e.g., semantic understanding and communication). This pipeline is prevalent in a variety of applications [1]- [3], such as smart communities [4], and surveillance systems [5]. For instance, instantaneous RGB snapshots enable the detection of driving lanes or pedestrians in advanced driver assistance systems [6] to improve road safety and risk prevention.…”

A Blockchain-Enabled Trusted Protocol Based on Whole-Process User Behavior in 6G Network

“…It is assumed that n users are accessing the network through the access gateway at time t. In (6), f is the trusted authentication protocol reflecting the relationship between IAR and IAB. IAB t i and IAR t i represent the IAB and IAR of user u i at time t, respectively.…”

“…e Sixth-Generation (6G) network realizes borderless connection under the global coverage, and enables the ubiquitous connectivity of massive users and devices by thoroughly integrating multiple heterogeneous networks, including satellite, air, ground, and sea networks [1][2][3]. e access of a large number of users and devices increases the potential risk of network attacks, bringing great challenges to network security [4][5][6]. e Trusted Protocol (TP) can effectively reduce the attacks launched by malicious users on the network by controlling and managing user behaviors, which is one of the important methods to improve network security [7][8][9].…”

Game-Theoretical Data Offloading for NOMA-Enabled Urban Internet of Things

“…But this paper did not consider the complex data access of multiple BSs. In [40], the authors proposed an intelligent video application based on interference-aware data offloading, which can be combined with real-time traffic monitoring 12 Wireless Communications and Mobile Computing to improve urban IoT. The authors in [41] considered the energy-saving task offloading problem based on stochastic optimization in MEC, which minimizes the energy consumption of task offloading while ensuring the average queue length.…”