Using Deep Learning to Identify Utility Poles with Crossarms and Estimate Their Locations from Google Street View Images

Zhang, Weixing; Witharana, Chandi; Li, Weidong; Zhang, Chuanrong; Li, Xiaojiang; Parent, Jason

doi:10.3390/s18082484

Cited by 57 publications

(36 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep neural networks are reported to be effective to extract useful semantic information from street view images [21,30,55]. In our study, semantic features of street view images are firstly extracted by Places-CNN which is a deep convolutional neural network used for ground-level scene recognition.…”

Section: Semantic Feature Extractionmentioning

confidence: 99%

Integrating Aerial and Street View Images for Urban Land Use Classification

et al. 2018

View full text Add to dashboard Cite

Urban land use is key to rational urban planning and management. Traditional land use classification methods rely heavily on domain experts, which is both expensive and inefficient. In this paper, deep neural network-based approaches are presented to label urban land use at pixel level using high-resolution aerial images and ground-level street view images. We use a deep neural network to extract semantic features from sparsely distributed street view images and interpolate them in the spatial domain to match the spatial resolution of the aerial images, which are then fused together through a deep neural network for classifying land use categories. Our methods are tested on a large publicly available aerial and street view images dataset of New York City, and the results show that using aerial images alone can achieve relatively high classification accuracy, the ground-level street view images contain useful information for urban land use classification, and fusing street image features with aerial images can improve classification accuracy. Moreover, we present experimental studies to show that street view images add more values when the resolutions of the aerial images are lower, and we also present case studies to illustrate how street view images provide useful auxiliary information to aerial images to boost performances.

show abstract

Section: Semantic Feature Extractionmentioning

confidence: 99%

Integrating Aerial and Street View Images for Urban Land Use Classification

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Street-level imagery data, such as Google Street View (GSV), provide extensive geographical coverage, and standardized, geocoded and high resolution images of the urban environment. Computer vision algorithms have been developed to process street-level imagery, measuring perceived urban safety [21], urban change [22], wealth [23], infrastructure [24], demographics [25] and building type classification [26]. In the context of urban trees, a small but growing number of studies have sought to develop computer vision approaches to address three key areas: (1) quantify the shade provision of urban canopy [27][28][29]; (2) catalog the location of urban trees [30,31]; and, (3) estimate the percent of urban street-level tree cover [15,20,32,33].…”

Section: Introductionmentioning

confidence: 99%

A Hierarchical Urban Forest Index Using Street-Level Imagery and Deep Learning

et al. 2019

View full text Add to dashboard Cite

We develop a method based on computer vision and a hierarchical multilevel model to derive an Urban Street Tree Vegetation Index which aims to quantify the amount of vegetation visible from the point of view of a pedestrian. Our approach unfolds in two steps. First, areas of vegetation are detected within street-level imagery using a state-of-the-art deep neural network model. Second, information is combined from several images to derive an aggregated indicator at the area level using a hierarchical multilevel model. The comparative performance of our proposed approach is demonstrated against a widely used image segmentation technique based on a pre-labelled dataset. The approach is deployed to a real-world scenario for the city of Cardiff, Wales, using Google Street View imagery. Based on more than 200,000 street-level images, an urban tree street-level indicator is derived to measure the spatial distribution of tree cover, accounting for the presence of obstructing objects present in images at the Lower Layer Super Output Area (LSOA) level, corresponding to the most commonly used administrative areas for policy-making in the United Kingdom. The results show a high degree of correspondence between our tree street-level score and aerial tree cover estimates. They also evidence more accurate estimates at a pedestrian perspective from our tree score by more appropriately capturing tree cover in areas with large burial, woodland, formal open and informal open spaces where shallow trees are abundant, in high density residential areas with backyard trees, and along street networks with high density of high trees. The proposed approach is scalable and automatable. It can be applied to cities across the world and provides robust estimates of urban trees to advance our understanding of the link between mental health, well-being, green space and air pollution.

show abstract

“…The same authors extend their approach by adding LiDAR data for object segmentation, triangulation, and monocular depth estimation for traffic lights . Zhang et al (2018) propose a CNN-based object detector for poles and apply a line-of-bearing method to estimate the geographic object position. In this paper, we advocate for a simplified version of (Wegner et al, 2016;Branson et al, 2018) for tree detection and geo-localization that is less costly to compute then a full end-to-end approach (Nassar et al, 2019b) at very large scale (i.e., 48 cities in California.…”

Section: Related Workmentioning

confidence: 99%

Geocoding of trees from street addresses and street-level images

Laumer

Lang

Doorn

et al. 2020

ISPRS Journal of Photogrammetry and Remote Sensing

View full text Add to dashboard Cite

We introduce an approach for updating older tree inventories with geographic coordinates using street-level panorama images and a global optimization framework for tree instance matching. Geolocations of trees in inventories until the early 2000s where recorded using street addresses whereas newer inventories use GPS. Our method retrofits older inventories with geographic coordinates to allow connecting them with newer inventories to facilitate long-term studies on tree mortality etc. What makes this problem challenging is the different number of trees per street address, the heterogeneous appearance of different tree instances in the images, ambiguous tree positions if viewed from multiple images and occlusions. To solve this assignment problem, we (i) detect trees in Google street-view panoramas using deep learning, (ii) combine multi-view detections per tree into a single representation, (iii) and match detected trees with given trees per street address with a global optimization approach. Experiments for > 50000 trees in 5 cities in California, USA, show that we are able to assign geographic coordinates to 38 % of the street trees, which is a good starting point for long-term studies on the ecosystem services value of street trees at large scale.

show abstract

Using Deep Learning to Identify Utility Poles with Crossarms and Estimate Their Locations from Google Street View Images

Cited by 57 publications

References 58 publications

Integrating Aerial and Street View Images for Urban Land Use Classification

Integrating Aerial and Street View Images for Urban Land Use Classification

A Hierarchical Urban Forest Index Using Street-Level Imagery and Deep Learning

Geocoding of trees from street addresses and street-level images

Contact Info

Product

Resources

About