Accurate Specified-Pedestrian Tracking from Unmanned Aerial Vehicles

Yang, Zhen; Huang, Zhiyi; Yang, Yanhui; Yang, Fan; Yin, Zhijian

doi:10.1109/icct.2018.8600173

Cited by 7 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regarding variable O&M, discussions with Yang (2018) gave a cost of $2/kWh for the year 2022. For this work, the research team have aligned O&M costs with other battery technologies.…”

Section: Fixed and Variable Operations And Maintenance Costsmentioning

confidence: 99%

“…It is projected to endure 5,000 cycles at 100% DoD, or a 15-year calendar life. The DC-DC RTE projections for 2022 was stated to be 75 percent from Yang (2018), while the DC response time was a few milliseconds to rated power. For this work, the AC-AC RTE was assumed to be 72 percent, while AC response time was assumed to be 1 second.…”

Section: Cycles Lifespan and Efficiencymentioning

confidence: 99%

See 1 more Smart Citation

Energy Storage Technology and Cost Characterization Report

Mongird¹,

Viswanathan²,

Balducci³

et al. 2019

286

207

View full text Add to dashboard Cite

This report defines and evaluates cost and performance parameters of six battery energy storage technologies (BESS) (lithium-ion batteries, lead-acid batteries, redox flow batteries, sodium-sulfur batteries, sodium metal halide batteries, and zinc-hybrid cathode batteries) and four non-BESS storage technologies (pumped storage hydropower, flywheels, compressed air energy storage, and ultracapacitors). Data for combustion turbines are also presented. Cost information was procured for the most recent year for which data were available based on an extensive literature review, conversations with vendors and stakeholders, and summaries of actual costs provided from specific projects at sites across the United States. Detailed cost and performance estimates were presented for 2018 and projected out to 2025.

show abstract

“…Regarding variable O&M, discussions with Yang (2018) gave a cost of $2/kWh for the year 2022. For this work, the research team have aligned O&M costs with other battery technologies.…”

Section: Fixed and Variable Operations And Maintenance Costsmentioning

confidence: 99%

Section: Cycles Lifespan and Efficiencymentioning

confidence: 99%

Energy Storage Technology and Cost Characterization Report

Mongird¹,

Viswanathan²,

Balducci³

et al. 2019

286

207

View full text Add to dashboard Cite

show abstract

“…Human action detection in aerial images is closely related to pedestrian detection and tracking in UAV videos [14,15]. Liu et al [16] applied the Yolo architecture to small object detection in UAV image data.…”

Section: Introductionmentioning

confidence: 99%

Detecting Human Actions in Drone Images Using YoloV5 and Stochastic Gradient Boosting

Ahmad

Cavazza

Matsuo

et al. 2022

Sensors

View full text Add to dashboard Cite

Human action recognition and detection from unmanned aerial vehicles (UAVs), or drones, has emerged as a popular technical challenge in recent years, since it is related to many use case scenarios from environmental monitoring to search and rescue. It faces a number of difficulties mainly due to image acquisition and contents, and processing constraints. Since drones’ flying conditions constrain image acquisition, human subjects may appear in images at variable scales, orientations, and occlusion, which makes action recognition more difficult. We explore low-resource methods for ML (machine learning)-based action recognition using a previously collected real-world dataset (the “Okutama-Action” dataset). This dataset contains representative situations for action recognition, yet is controlled for image acquisition parameters such as camera angle or flight altitude. We investigate a combination of object recognition and classifier techniques to support single-image action identification. Our architecture integrates YoloV5 with a gradient boosting classifier; the rationale is to use a scalable and efficient object recognition system coupled with a classifier that is able to incorporate samples of variable difficulty. In an ablation study, we test different architectures of YoloV5 and evaluate the performance of our method on Okutama-Action dataset. Our approach outperformed previous architectures applied to the Okutama dataset, which differed by their object identification and classification pipeline: we hypothesize that this is a consequence of both YoloV5 performance and the overall adequacy of our pipeline to the specificities of the Okutama dataset in terms of bias–variance tradeoff.

show abstract

A Sparse-Dense HOG Window Sampling Technique for Fast Pedestrian Detection in Aerial Images

Kumar¹,

Deb²

2022

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

Accurate Specified-Pedestrian Tracking from Unmanned Aerial Vehicles

Cited by 7 publications

References 14 publications

Energy Storage Technology and Cost Characterization Report

Energy Storage Technology and Cost Characterization Report

Detecting Human Actions in Drone Images Using YoloV5 and Stochastic Gradient Boosting

A Sparse-Dense HOG Window Sampling Technique for Fast Pedestrian Detection in Aerial Images

Contact Info

Product

Resources

About