scale point
Recently Published Documents





2022 ◽  
Vol 193 ◽  
pp. 106653
Hejun Wei ◽  
Enyong Xu ◽  
Jinlai Zhang ◽  
Yanmei Meng ◽  
Jin Wei ◽  

2022 ◽  
Yuehua Zhao ◽  
Ma Jie ◽  
Chong Nannan ◽  
Wen Junjie

Abstract Real time large scale point cloud segmentation is an important but challenging task for practical application like autonomous driving. Existing real time methods have achieved acceptance performance by aggregating local information. However, most of them only exploit local spatial information or local semantic information dependently, few considering the complementarity of both. In this paper, we propose a model named Spatial-Semantic Incorporation Network (SSI-Net) for real time large scale point cloud segmentation. A Spatial-Semantic Cross-correction (SSC) module is introduced in SSI-Net as a basic unit. High quality contextual features can be learned through SSC by correct and update semantic features using spatial cues, and vice verse. Adopting the plug-and-play SSC module, we design SSI-Net as an encoder-decoder architecture. To ensure efficiency, it also adopts a random sample based hierarchical network structure. Extensive experiments on several prevalent datasets demonstrate that our method can achieve state-of-the-art performance.

Lei Wang ◽  
Jiaji Wu ◽  
Xunyu Liu ◽  
Xiaoliang Ma ◽  
Jun Cheng

AbstractThree-dimensional (3D) semantic segmentation of point clouds is important in many scenarios, such as automatic driving, robotic navigation, while edge computing is indispensable in the devices. Deep learning methods based on point sampling prove to be computation and memory efficient to tackle large-scale point clouds (e.g. millions of points). However, some local features may be abandoned while sampling. In this paper, We present one end-to-end 3D semantic segmentation framework based on dilated nearest neighbor encoding. Instead of down-sampling point cloud directly, we propose a dilated nearest neighbor encoding module to broaden the network’s receptive field to learn more 3D geometric information. Without increase of network parameters, our method is computation and memory efficient for large-scale point clouds. We have evaluated the dilated nearest neighbor encoding in two different networks. The first is the random sampling with local feature aggregation. The second is the Point Transformer. We have evaluated the quality of the semantic segmentation on the benchmark 3D dataset S3DIS, and demonstrate that the proposed dilated nearest neighbor encoding exhibited stable advantages over baseline and competing methods.

2021 ◽  
Vol 4 (4) ◽  
pp. 100
Partha Pratim Ray ◽  
Dinesh Dash

Anomaly detection in the smart application domain can significantly improve the quality of data processing, especially when the size of a dataset is too small. Internet of Things (IoT) enables the development of numerous applications where sensor-data-aware anomalies can affect the decision making of the underlying system. In this paper, we propose a scheme: IoTDixon, which works on the Dixon’s Q test to identify point anomalies from a simulated normally distributed dataset. The proposed technique involves Q statistics, Kolmogorov–Smirnov test, and partitioning of a given dataset into a specific data packet. The proposed techniques use Q-test to detect point anomalies. We find that value 76.37 is statistically significant where P=0.012<α=0.05, thus rejecting the null hypothesis for a test data packet. In other data packets, no such significance is observed; thus, no outlier is statistically detected. The proposed approach of IoTDixon can help to improve small-scale point anomaly detection for a small-size dataset as shown in the conducted experiments.

2021 ◽  
Vol 182 ◽  
pp. 37-51
Jing Du ◽  
Guorong Cai ◽  
Zongyue Wang ◽  
Shangfeng Huang ◽  
Jinhe Su ◽  

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Siti Nurdiyana Atikah Sulaiman ◽  
Mohammad Nabil Almunawar

Purpose The purpose of this paper is to investigate factors that influence customers’ adoption of biometric-based point-of-sale in Brunei. Design/methodology/approach This paper extends technology acceptance model constructs with trust and some other variables as the framework to investigate their influence on the attitude toward the usage of a biometric point-of-sale terminal for payments in Brunei. Nine variables may influence user’s perception toward usage. The nine variables are needed, perceived ease of use, perceived usefulness, experience, innovativeness, privacy, security, trust and attitude toward usage. Multiple regression analysis was conducted to test hypotheses related to these nine variables. Findings It is found that the innovativeness of an individual and similar experience corresponds toward trust, which is positively related to attitude toward usage. Perceived usefulness and trust have significantly influenced the intention of individuals to use biometrics as an authentication method for payment. Research limitations/implications The nature of this research is to gather the public’s opinion and perception as much as it is deemed possible to get a bigger and clearer picture of the study. As the target respondence is citizens and residents of Brunei without any specification or exclusion, a large response would be needed to have a more reliable and accurate result. However, only 205 respondents can be gathered in this study. Had there been a longer time frame, it would be best to gather a lot more responses. Originality/value This paper explores the adoption of biometric authentication in large-scale point-of-terminals. It identifies factors that influence adoption. The results of this study could assist future researchers in which direction to take to further explore biometric as an authentication method for payment. In addition to this, it could also provide banks and financial technology in Brunei a clearer picture of the Brunei market and Bruneians perspective on the biometric system.

Yuan Zhou ◽  
qi sun ◽  
Jin Meng ◽  
Qinglong Hu ◽  
Jiahang Lyv ◽  

2021 ◽  
Siqi Fan ◽  
Qiulei Dong ◽  
Fenghua Zhu ◽  
Yisheng Lv ◽  
Peijun Ye ◽  

Sign in / Sign up

Export Citation Format

Share Document