Real-Time Traffic Flow Parameter Estimation From UAV Video Based on Ensemble Classifier and Optical Flow

Ke, Ruimin; Li, Zhibin; Tang, Jinjun; Pan, Zewen; Wang, Yinhai

doi:10.1109/tits.2018.2797697

Cited by 217 publications

(118 citation statements)

References 31 publications

Supporting

Mentioning

117

Contrasting

Unclassified

Order By: Relevance

“…For example, we can replace the BM and subtraction methods shown in Fig. 1 to optical flow methods [37], [38]. By using CARF, boosting the computation speed and obtaining high-quality results of recent optical flow methods without additional hardware implementation [39] can be achieved.…”

Section: Discussionmentioning

confidence: 99%

A Content-Adaptive Resizing Framework for Boosting Computation Speed of Background Modeling Methods

Huang

Liao

et al. 2022

IEEE Trans. Syst. Man Cybern, Syst.

View full text Add to dashboard Cite

Recently, most background modeling (BM) methods claim to achieve real-time efficiency for low-resolution and standard-definition surveillance videos. With the increasing resolutions of surveillance cameras, full high-definition (full HD) surveillance videos have become the main trend and thus processing high-resolution videos becomes a novel issue in intelligent video surveillance. In this article, we propose a novel contentadaptive resizing framework (CARF) to boost the computation speed of BM methods in high-resolution surveillance videos. For each frame, we apply superpixels to separate the content of the frame to homogeneous and boundary sets. Two novel downsampling and upsampling layers based on the homogeneous and boundary sets are proposed. The front one downsamples highresolution frames to low-resolution frames for obtaining efficient foreground segmentation results based on BM methods. The later one upsamples the low-resolution foreground segmentation results to the original resolution frames based on the superpixels. By simultaneously coupling both layers, experimental results show that the proposed method can achieve better quantitative and qualitative results compared with state-of-the-art methods. Moreover, the computation speed of the proposed method without GPU accelerations is also significantly faster than that of the state-of-the-art methods. The source code is available at https://github.com/nchucvml/CARF. Index Terms-Background modeling (BM), frame downsampling, frame resizing, frame upsampling, superpixels. I. INTRODUCTION B ACKGROUND modeling (BM) methods are shown to be effective and efficient for foreground segmentation in intelligent video surveillance (IVS) [1]. It serves as one Manuscript

show abstract

Section: Discussionmentioning

confidence: 99%

A Content-Adaptive Resizing Framework for Boosting Computation Speed of Background Modeling Methods

Huang

Liao

et al. 2022

IEEE Trans. Syst. Man Cybern, Syst.

View full text Add to dashboard Cite

show abstract

“…Classifying with Haar cascades is admitted as fast and simple method for analyzing video in real time. This method is based on Haarlike features [15]. The high accuracy of object description requires the presence of big number of features.…”

Section: Object Detection and Classificationmentioning

confidence: 99%

Methods of Semantic Integrity Preservation in the Pattern Recognition Process

Kim

Matveeva

Viksnin

et al. 2019

International Journal of Embedded and Real-Time Communication Systems

View full text Add to dashboard Cite

Computer vision is a wide area of theoretical research and technical methods connected with object detection, object tracking and object classification. In this article computer vision is considered in context of embedding it into automobiles in order to automate the road traffic process through video stream analysis. During road traffic it is vital to detect objects quickly and correctly, so the authors pay attention to the pattern recognition quality, especially to the visual information semantic integrity preservation. Their main purpose is to find the ways of its possible improvement respectively to three basic stages of the pattern recognition process. To avoid semantic integrity violations of information in the initial stage of the image analysis the authors propose normalization; in the second stage new clustering method was developed based on particle swarm optimization and k-means algorithm; in the final stage of the pattern recognition process the Haar cascade classifier was used with normalized training samples. The obtained image processing algorithm was implemented in case of blurred and noisy images and proved its effectiveness respectively to the visual information semantic integrity preservation.

show abstract

“…UAV application fields are further specified in [2], where the operational ranges of these platforms with respect to other geomatics techniques, and depending on the dimension and complexity of the surveyed area, are detailed and discussed. Nex and Remondino identified six main UAV application fields (that were addressed by several research groups), namely: agriculture [3][4][5][6], forestry [7][8][9][10], archaeology and architecture [11][12][13][14][15][16][17], the environment [18][19][20][21], emergency management [22][23][24], and traffic monitoring [25][26][27][28].…”

Section: Introductionmentioning

confidence: 99%

Boosting the Timeliness of UAV Large Scale Mapping. Direct Georeferencing Approaches: Operational Strategies and Best Practices

Losè

Chiabrando

Tonolo

2020

IJGI

View full text Add to dashboard Cite

The use of unmanned aerial vehicles (UAVs) is nowadays a standard approach in several application fields. Researches connected with these systems cover several topics and the evolution of these platforms and their applications are rapidly growing. Despite the high level of automatization reached nowadays, there is still a phase of the overall UAVs’ photogrammetric pipeline that requires a high effort in terms of time and resources (i.e., the georeferencing phase). However, thanks to the availability of survey-grade GNSS (Global Navigation Satellite System) receivers embedded in the aerial platforms, it is possible to also enhance this phase of the processing by adopting direct georeferencing approaches (i.e., without using any ground control point and exploiting real time kinematic (RTK) positioning). This work investigates the possibilities offered by a multirotor commercial system equipped with a RTK-enabled GNSS receiver, focusing on the accuracy of the georeferencing phase. Several tests were performed in an ad-hoc case study exploiting different georeferencing solutions and assessing the 3D positional accuracies, thanks to a network of control points. The best approaches to be adopted in the field according to accuracy requirements of the final map products were identified and operational guidelines proposed accordingly.

show abstract

Real-Time Traffic Flow Parameter Estimation From UAV Video Based on Ensemble Classifier and Optical Flow

Cited by 217 publications

References 31 publications

A Content-Adaptive Resizing Framework for Boosting Computation Speed of Background Modeling Methods

A Content-Adaptive Resizing Framework for Boosting Computation Speed of Background Modeling Methods

Methods of Semantic Integrity Preservation in the Pattern Recognition Process

Boosting the Timeliness of UAV Large Scale Mapping. Direct Georeferencing Approaches: Operational Strategies and Best Practices

Contact Info

Product

Resources

About