MDPI - Publisher of Open Access Journals

22 pages, 4126 KiB

Open AccessArticle

Adaptive Local Spatiotemporal Features from RGB-D Data for One-Shot Learning Gesture Recognition

by Jia Lin, Xiaogang Ruan, Naigong Yu and Yee-Hong Yang

Sensors 2016, 16(12), 2171; https://doi.org/10.3390/s16122171 - 17 Dec 2016

Cited by 6 | Viewed by 5819

Noise and constant empirical motion constraints affect the extraction of distinctive spatiotemporal features from one or a few samples per gesture class. To tackle these problems, an adaptive local spatiotemporal feature (ALSTF) using fused RGB-D data is proposed. First, motion regions of interest (MRoIs) are adaptively extracted using grayscale and depth velocity variance information to greatly reduce the impact of noise. Then, corners are used as keypoints if their depth, and velocities of grayscale and of depth meet several adaptive local constraints in each MRoI. With further filtering of noise, an accurate and sufficient number of keypoints is obtained within the desired moving body parts (MBPs). Finally, four kinds of multiple descriptors are calculated and combined in extended gradient and motion spaces to represent the appearance and motion features of gestures. The experimental results on the ChaLearn gesture, CAD-60 and MSRDailyActivity3D datasets demonstrate that the proposed feature achieves higher performance compared with published state-of-the-art approaches under the one-shot learning setting and comparable accuracy under the leave-one-out cross validation. Full article

(This article belongs to the Special Issue Video Analysis and Tracking Using State-of-the-Art Sensors)

► Show Figures

Figure 1

21 pages, 937 KiB

Open AccessArticle

A Preliminary Forecast of the Production Status of China’s Daqing Oil field from the Perspective of EROI

by Bo Xu, Lianyong Feng, William X. Wei, Yan Hu and Jianliang Wang

Sustainability 2014, 6(11), 8262-8282; https://doi.org/10.3390/su6118262 - 18 Nov 2014

Cited by 14 | Viewed by 7770

Abstract

Energy return on investment (EROI) and net energy are useful metrics for analyzing energy production physically rather than monetarily. However, these metrics are not widely applied in China. In this study, we forecast the Daqing oilfield’s EROI from 2013 to 2025 using existing data for crude oil and natural gas production and the basic rules of EROI. Unfortunately, our calculations indicate that the oilfield’s EROI will continuously decline from 7.3 to 4.7, and the associated net energy will continuously decline from 1.53 × 10¹² MJ to 1.25 × 10¹² MJ. If China’s energy intensity does not decline as planned in the next ten years, then the EROI of Daqing will be even lower than our estimates. Additionally, relating the EROI to the monetary return on investment (MROI) in a low production and high intensity scenario, Daqing’s EROI will decline to 2.9 and its MROI will decline to 1.8 by 2025. If the “law of minimum EROI” and the assumed “minimum MROI” are taken into account, then we estimate that both energy pressure and economic pressure will restrict Daqing’s production by 2025. Full article

(This article belongs to the Section Energy Sustainability)

► Show Figures

Figure 1

Search Results (2)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI

Saved Queries

Search Filter Reset All

Years

Feature Papers

Subjects

Journals

Article Types

Countries / Regions

Search Results (2)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI