scholarly journals Developing Sidewalk Inventory Data Using Street View Images

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 3300
Author(s):  
Bumjoon Kang ◽  
Sangwon Lee ◽  
Shengyuan Zou
Keyword(s):  
Detection Method ◽  
Random Forest Classifier ◽  
Inventory Data ◽  
City Development ◽  
Accuracy Rate ◽  
Street Level ◽  
Segmented Image ◽  
Street View ◽  
Image Segment ◽  
Gis Data

(1) Background: Public sidewalk GIS data are essential for smart city development. We developed an automated street-level sidewalk detection method with image-processing Google Street View data. (2) Methods: Street view images were processed to produce graph-based segmentations. Image segment regions were manually labeled and a random forest classifier was established. We used multiple aggregation steps to determine street-level sidewalk presence. (3) Results: In total, 2438 GSV street images and 78,255 segmented image regions were examined. The image-level sidewalk classifier had an 87% accuracy rate. The street-level sidewalk classifier performed with nearly 95% accuracy in most streets in the study area. (4) Conclusions: Highly accurate street-level sidewalk GIS data can be successfully developed using street view images.

scholarly journals A deep learning approach to identify unhealthy advertisements in street view images

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Gregory Palmer ◽  
Mark Green ◽  
Emma Boyland ◽  
Yales Stefano Rios Vasconcelos ◽  
Rahul Savani ◽  
...  
Keyword(s):  
Deep Learning ◽  
Fast Food ◽  
Social Inequalities ◽  
Social Inequalities In Health ◽  
Street Level ◽  
Street View ◽  
Food Advertisements ◽  
Data Collection Effort ◽  
Deprived Areas

AbstractWhile outdoor advertisements are common features within towns and cities, they may reinforce social inequalities in health. Vulnerable populations in deprived areas may have greater exposure to fast food, gambling and alcohol advertisements, which may encourage their consumption. Understanding who is exposed and evaluating potential policy restrictions requires a substantial manual data collection effort. To address this problem we develop a deep learning workflow to automatically extract and classify unhealthy advertisements from street-level images. We introduce the Liverpool $${360}^{\circ }$$ 360 ∘ Street View (LIV360SV) dataset for evaluating our workflow. The dataset contains 25,349, 360 degree, street-level images collected via cycling with a GoPro Fusion camera, recorded Jan 14th–18th 2020. 10,106 advertisements were identified and classified as food (1335), alcohol (217), gambling (149) and other (8405). We find evidence of social inequalities with a larger proportion of food advertisements located within deprived areas and those frequented by students. Our project presents a novel implementation for the incidental classification of street view images for identifying unhealthy advertisements, providing a means through which to identify areas that can benefit from tougher advertisement restriction policies for tackling social inequalities.

Joining Street-View Images and Building Footprint GIS Data

2021 ◽  
Author(s):  
Yoshiki Ogawa ◽  
Takuya Oki ◽  
Shenglong Chen ◽  
Yoshihide Sekimoto
Keyword(s):  
Street View ◽  
Gis Data ◽  
Building Footprint

scholarly journals Estimation of Mean Radiant Temperature in Urban Canyons Using Google Street View: A Case Study on Seoul

2022 ◽  
Vol 14 (2) ◽  
pp. 260
Author(s):  
Eun-Sub Kim ◽  
Seok-Hwan Yun ◽  
Chae-Yeon Park ◽  
Han-Kyul Heo ◽  
Dong-Kun Lee
Keyword(s):  
Heat Stress ◽  
Spatial Patterns ◽  
High Density ◽  
View Factor ◽  
Mean Radiant Temperature ◽  
Street Canyons ◽  
Google Street View ◽  
Street Level ◽  
Street View ◽  
Radiant Temperature

Extreme heat exposure has severe negative impacts on humans, and the issue is exacerbated by climate change. Estimating spatial heat stress such as mean radiant temperature (MRT) is currently difficult to apply at city scale. This study constructed a method for estimating the MRT of street canyons using Google Street View (GSV) images and investigated its large-scale spatial patterns at street level. We used image segmentation using deep learning to calculate the view factor (VF) and project panorama into fisheye images. We calculated sun paths to estimate MRT using panorama images from Google Street View. This paper shows that regression analysis can be used to validate between estimated short-wave, long-wave radiation and the measurement data at seven field measurements in the clear-sky (0.97 and 0.77, respectively). Additionally, we compared the calculated MRT and land surface temperature (LST) from Landsat 8 on a city scale. As a result of investigating spatial patterns of MRT in Seoul, South Korea, we found that a high MRT of street canyons (>59.4 °C) is mainly distributed in open space areas and compact low-rise density buildings where the sky view factor is 0.6–1.0 and the building view factor (BVF) is 0.35–0.5, or west-east oriented street canyons with an SVF of 0.3–0.55. However, high-density buildings (BVF: 0.4–0.6) or high-density tree areas (Tree View Factor, TVF: 0.6–0.99) showed low MRT (<47.6). The mapped MRT results had a similar spatial distribution to the LST; however, the MRT was lower than the LST in low tree density or low-rise high-density building areas. The method proposed in this study is suitable for a complex urban environment consisting of buildings, trees, and streets. This will help decision makers understand spatial patterns of heat stress at the street level.

scholarly journals About the benefits of poststratification in forest inventories

2008 ◽  
Vol 53 (No. 4) ◽  
pp. 139-148 ◽  
Author(s):  
J. Saborowski ◽  
J. Cancino
Keyword(s):  
Large Scale ◽  
Systematic Sampling ◽  
Inventory Data ◽  
Sample Sizes ◽  
Forest Inventories ◽  
Virtual Population ◽  
Random Samples ◽  
Gis Data ◽  
Forest District ◽  
Unconditional Variance

A large virtual population is created based on the GIS data base of a forest district and inventory data. It serves as a population where large scale inventories with systematic and simple random poststratified estimators can be simulated and the gains in precision studied. Despite their selfweighting property, systematic samples combined with poststratification can still be clearly more efficient than unstratified systematic samples, the gain in precision being close to that resulting from poststratified over simple random samples. The poststratified variance estimator for the conditional variance given the within strata sample sizes served as a satisfying estimator in the case of systematic sampling. The differences between conditional and unconditional variance were negligible for all sample sizes analyzed.

scholarly journals An API Semantics-Aware Malware Detection Method Based on Deep Learning

2019 ◽  
Vol 2019 ◽  
pp. 1-9 ◽  
Author(s):  
Xin Ma ◽  
Shize Guo ◽  
Wei Bai ◽  
Jun Chen ◽  
Shiming Xia ◽  
...  
Keyword(s):  
Machine Learning ◽  
Detection Method ◽  
Malware Detection ◽  
Poor Performance ◽  
Detection Methods ◽  
Interference Detection ◽  
Machine Learning Method ◽  
Accuracy Rate ◽  
Malware Classification ◽  
Self Protection

The explosive growth of malware variants poses a continuously and deeply evolving challenge to information security. Traditional malware detection methods require a lot of manpower. However, machine learning has played an important role on malware classification and detection, and it is easily spoofed by malware disguising to be benign software by employing self-protection techniques, which leads to poor performance for existing techniques based on the machine learning method. In this paper, we analyze the local maliciousness about malware and implement an anti-interference detection framework based on API fragments, which uses the LSTM model to classify API fragments and employs ensemble learning to determine the final result of the entire API sequence. We present our experimental results on Ali-Tianchi contest API databases. By comparing with the experiments of some common methods, it is proved that our method based on local maliciousness has better performance, which is a higher accuracy rate of 0.9734.

Multi-Target Tracking Based on Regional Correlation and Color Histogram Match

2014 ◽  
Vol 998-999 ◽  
pp. 631-637
Author(s):  
Shou Hua Yu ◽  
Ji Hong Chen ◽  
Jing Ying Ou ◽  
Dan Chun Xu
Keyword(s):  
Target Tracking ◽  
Detection Method ◽  
Color Histogram ◽  
False Detection ◽  
Accuracy Rate ◽  
Regional Correlation ◽  
Multi Target Tracking ◽  
Long Time ◽  
The Difference ◽  
Difference Images

A method based on regional correlation and color histogram match was proposed for multi-target adaptive tracking. Firstly, target detection method was used to get the difference images. Then, the same target could be recognized according to the correlation of target regions of consecutive frames and the matching rate of color histogram. Finally, the active value, lifetime and dormancy value of targets were used to carry out long-time target tracking and deal with the problems of missing detection, false detection and target exit. The experiment shows that the method proposed in this paper has reached to a high accuracy rate of 95%, which has good robustness against the processing of missing detection, false detection and target exit.

scholarly journals ECG-Based Subject Identification Using Statistical Features and Random Forest

2019 ◽  
Vol 2019 ◽  
pp. 1-13 ◽  
Author(s):  
Turky N. Alotaiby ◽  
Saud Rashid Alrshoud ◽  
Saleh A. Alshebeili ◽  
Latifah M. Aljafar
Keyword(s):  
Random Forest ◽  
Random Forest Classifier ◽  
Ecg Signal ◽  
Identification Algorithm ◽  
Statistical Features ◽  
Accuracy Rate ◽  
Subject Identification ◽  
Signal Segment ◽  
Electrocardiogram Ecg ◽  
Ecg Database

In this work, a nonfiducial electrocardiogram (ECG) identification algorithm based on statistical features and random forest classifier is presented. Two feature extraction approaches are investigated: direct and band-based approaches. In the former, eleven simple statistical features are directly extracted from a single-lead ECG signal segment. In the latter, the single-lead ECG signal is first decomposed into bands, and the statistical features are extracted from each segment of a given band and concatenated to form the feature vector. Nonoverlapping segments of different lengths (i.e., 1, 3, 5, 7, 10, or 15 sec) are examined. The extracted feature vectors are applied to a random forest classifier, for the purpose of identification. This study considers 290 reference subjects from the ECG database of the Physikalisch-Technische Bundesanstalt (PTB). The proposed identification algorithm achieved an accuracy rate of 99.61% utilizing the single limb lead (I) with the band-based approach. A single chest lead (V1), augmented limb lead (aVF), and Frank’s lead (Vx) achieved an accuracy rate of 99.37%, 99.76%, and 99.76%, respectively, using the same approach.

scholarly journals Association-based Concealed Information Test: A Novel Reaction Time-Based Deception Detection Method

2019 ◽  
Author(s):  
Gáspár Lukács ◽  
Bartosz Gula ◽  
Emese Szegedi-Hallgató ◽  
Gábor Csifcsák
Keyword(s):  
Reaction Time ◽  
Deception Detection ◽  
Detection Method ◽  
Concealed Information Test ◽  
Accuracy Rate ◽  
Probe Item ◽  
Subject Design ◽  
Limited Applicability ◽  
Concealed Information ◽  
Information Test

In recent years, numerous studies were published on the reaction time (RT)-based Concealed Information Test (CIT). However, an important limitation of the CIT is the reliance on the recognition of the probe item, and therefore the limited applicability when an innocent person is aware of this item. In the present paper, we introduce an RT-based CIT that is based on item-category associations: the Association-based Concealed Information Test (A-CIT). Using the participants’ given names as probe items and self-referring “inducer” items (e.g., “MINE” or “ME”) that establish an association between ownership and responses choices, in Experiment 1 (within-subject design; n = 27), this method differentiated with high accuracy between guilty and innocent conditions. Experiment 2 (n = 25) replicated Experiment 1, except that the participants were informed of the probe item in the innocent condition—nonetheless, the accuracy rate remained high. Implications and future possibilities are discussed.

scholarly journals Face Recognition Based on Viola-Jones Face Detection Method and Local Binary Pattern (LBP)

2019 ◽  
pp. 50-55
Keyword(s):  
Feature Extraction ◽  
Face Recognition ◽  
Face Detection ◽  
Local Binary Pattern ◽  
Detection Method ◽  
Histogram Equalization ◽  
Face Image ◽  
Accuracy Rate ◽  
Data Set ◽  
Testing Phase

In this paper, the system consists of many steps, the first step includes the histogram equalization, detection, feature extraction, and classification. At first, the data set of a face image is segmented into four segments, after that Local Binary Pattern (LBP) algorithm is performed to extract features for each segment. The best feature vectors for all persons are stored in a new dataset in the next stage in order to be used in the testing phase. Finally, the accuracy rate of performance is evaluated to prove its robustness. Experiments show satisfying results and more accuracy achieved by the paper.

Sign in / Sign up

Export Citation Format

Share Document