A fuzzy bounding box merging technique for moving object detection

Tu, Jilin; Amo, Ana del; Xu, Yi; Guari, Li; Chang, Ming-Ching; Sebastian, Thomas

doi:10.1109/nafips.2012.6291011

Cited by 6 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The north-bound APIs implement the same analyst-facing (northbound) APIs as the DNNs (DDS can simply forward any function call to DNNs), so the high-level applications (e.g., [51,58]) do not need to change and DDS can be deployed transparently from the analysts' perspective. The only difference is that DDS runs the DNN twice on the same video segment, so the two DNN inference results must be merged into a single result, which is logically similar to how DNNs internally merge redundant results (e.g., [73]).…”

Section: Dds Interfacementioning

confidence: 99%

Server-Driven Video Streaming for Deep Learning Inference

Pervaiz

Yuan

et al. 2020

Proceedings of the Annual Conference of the ACM Special Interest Group on Data Communication on the Applications, Technologies,

134

View full text Add to dashboard Cite

Video streaming is crucial for AI applications that gather videos from sources to servers for inference by deep neural nets (DNNs). Unlike traditional video streaming that optimizes visual quality, this new type of video streaming permits aggressive compression/pruning of pixels not relevant to achieving high DNN inference accuracy. However, much of this potential is left unrealized, because current video streaming protocols are driven by the video source (camera) where the compute is rather limited. We advocate that the video streaming protocol should be driven by real-time feedback from the server-side DNN. Our insight is twofold: (1) server-side DNN has more context about the pixels that maximize its inference accuracy; and (2) the DNN's output contains rich information useful to guide video streaming. We present DDS (DNN-Driven Streaming), a concrete design of this approach. DDS continuously sends a low-quality video stream to the server; the server runs the DNN to determine where to re-send with higher quality to increase the inference accuracy. We find that compared to several recent baselines on multiple video genres and vision tasks, DDS maintains higher accuracy while reducing bandwidth usage by upto 59% or improves accuracy by upto 9% with no additional bandwidth usage.

show abstract

Section: Dds Interfacementioning

confidence: 99%

Server-Driven Video Streaming for Deep Learning Inference

Pervaiz

Yuan

et al. 2020

Proceedings of the Annual Conference of the ACM Special Interest Group on Data Communication on the Applications, Technologies,

134

View full text Add to dashboard Cite

show abstract

“…The authors in [38] showed a combined performance estimation criterion by considering the veracity, real-time demand, and implementation on hardware of the tracking algorithm. In [39] we can find an algorithm that applies fuzzy rules to merge the detected bounding boxes into a unique cluster bounding box that covers a unique object. The abovementioned publications show that there are many existing methods to describe the similarity between bounding boxes, but none of them directly translate into the analysis of the trajectories created by the systems of these data.…”

Section: B Similarity Of Objects In Timementioning

confidence: 99%

Efficient Characterization Method for Big Automotive Datasets Used for Perception System Development and Verification

Kowalczyk¹,

Komorkiewicz²,

Skruch

et al. 2022

IEEE Access

View full text Add to dashboard Cite

T HE paper proposes a formal approach for describing and evaluating the datasets that are used in automotive applications for machine learning, testing, and validation purposes. Proper, that is, qualitative and quantitative characterization of the datasets can simplify the analysis, evaluation, and comparison of perception-based algorithms designed for highly automated vehicles. Such formalism is also needed to achieve compliance with the automotive industry safety standards that have been recently introduced. Characterization in the form of size or type of raw data, number of recognized and classified objects, and environmental parameters is not perfectly suitable for describing both the static and dynamic aspects of automotive datasets; therefore, another approach is required. In this paper, an efficient method based on an object tracking mechanism, grid representation of the sensor field of view, heatmap concept, and Wasserstein metric is proposed. The efficiency of the method is demonstrated by its ability to handle both the size, properties, and diversity of the dataset, including static and time-varying aspects. The presented description can also be used to compare different datasets and to define the amount of data to be collected.

show abstract

“…We want to underline that, for similar cases, precision and possibility to decompose information is very important. Authors in [44] presented a combined criterion of performance evaluation by considering the veracity, real-time demand, and the implementation on hardware of the tracking algorithm, In [45], we can find an algorithm that derives fuzzy rules to merge the detected bounding boxes into a unique cluster bounding box that covers a unique object. Authors underline the need for a tool that describes relationships of a pair of boxes by their box geometrical affinity, by their motion cohesion, and their appearance similarity.…”

Section: Related Workmentioning

confidence: 99%

Evaluation Methodology for Object Detection and Tracking in Bounding Box Based Perception Modules

Kowalczyk

Izydorczyk

Szelest³

2022

Electronics

View full text Add to dashboard Cite

The aim of this work is to formulate a new metric to be used in the automotive industry for the evaluation process of software used to detect vehicles on video data. To achieve this goal, we have formulated a new concept for measuring the degree of matching between rectangles for industrial use. We propose new measure based on three sub-measures focused on the area of the rectangle, its shape, and distance. These sub-measures are merged into a General similarity measure to avoid problems with poor adaptability of the Jaccard index to practical issues of recognition. Additionally, we create method of calculation of detection quality in the sequence of video frames that summarizes the local quality and adds information about possible late detection. Experiments with real and artificial data have confirmed that we have created flexible tools that can reduce time needed to evaluate detection software efficiently, and provide more detailed information about the quality of detection than the Jaccard index. Their use can significantly speed up data analysis and capture the weaknesses and limitations of the detection system under consideration. Our detection quality assessment method can be of interest to all engineers involved in machine recognition of video data.

show abstract

A fuzzy bounding box merging technique for moving object detection

Cited by 6 publications

References 10 publications

Server-Driven Video Streaming for Deep Learning Inference

Server-Driven Video Streaming for Deep Learning Inference

Efficient Characterization Method for Big Automotive Datasets Used for Perception System Development and Verification

Evaluation Methodology for Object Detection and Tracking in Bounding Box Based Perception Modules

Contact Info

Product

Resources

About