Investigations on the Potential of Convolutional Neural Networks for Vehicle Classification Based on RGB and Lidar Data

Niessner, Robin; Schilling, Hendrik; Jutzi, Boris

doi:10.5194/isprs-annals-iv-1-w1-115-2017

Cited by 9 publications

(5 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As described in DECAF [39], it is possible to use a pre-trained ConvNet as feature generator and apply classical machine learning such as Support Vector Machine (SVM) or logistic regression to train a model with good performance. Transfer learning is utilized, such as classification of satellite images [42], vehicles detection based on RGB images or LiDAR data [43,44], visual floor count determination [45] or visual localization [46]. Only recently, this approach was used for retrieving flooding relevant social media photos [27,28].…”

Section: Related Methods For Interpreting Flood Relevant Social Mediamentioning

confidence: 99%

Extraction of Pluvial Flood Relevant Volunteered Geographic Information (VGI) by Deep Learning from User Generated Texts and Photos

Feng

Sester

2018

IJGI

View full text Add to dashboard Cite

Abstract:In recent years, pluvial floods caused by extreme rainfall events have occurred frequently. Especially in urban areas, they lead to serious damages and endanger the citizens' safety. Therefore, real-time information about such events is desirable. With the increasing popularity of social media platforms, such as Twitter or Instagram, information provided by voluntary users becomes a valuable source for emergency response. Many applications have been built for disaster detection and flood mapping using crowdsourcing. Most of the applications so far have merely used keyword filtering or classical language processing methods to identify disaster relevant documents based on user generated texts. As the reliability of social media information is often under criticism, the precision of information retrieval plays a significant role for further analyses. Thus, in this paper, high quality eyewitnesses of rainfall and flooding events are retrieved from social media by applying deep learning approaches on user generated texts and photos. Subsequently, events are detected through spatiotemporal clustering and visualized together with these high quality eyewitnesses in a web map application. Analyses and case studies are conducted during flooding events in Paris, London and Berlin.

show abstract

Section: Related Methods For Interpreting Flood Relevant Social Mediamentioning

confidence: 99%

Extraction of Pluvial Flood Relevant Volunteered Geographic Information (VGI) by Deep Learning from User Generated Texts and Photos

Feng

Sester

2018

IJGI

View full text Add to dashboard Cite

show abstract

“…A most widely adopted sensor for nonintrusive solutions is a camera [20] [21]. Significant advances in imaging technologies and image processing techniques based on machine learning algorithms gave a birth to precise camera-based TMSs [25]. As Table I shows, the classification accuracy of camera-based TMSs is very high.…”

Section: Related Workmentioning

confidence: 99%

DeepWiTraffic: Low Cost WiFi-Based Traffic Monitoring System Using Deep Learning

Won

Sahu

Park

2019

2019 IEEE 16th International Conference on Mobile Ad Hoc and Sensor Systems (MASS)

View full text Add to dashboard Cite

A traffic monitoring system (TMS) is an integral part of Intelligent Transportation Systems (ITS) for traffic analysis and planning. This paper addresses the endemic cost issue of deploying a large number of TMSs to cover huge miles of two-lane rural highways (119,247 miles in U.S.). A low-cost and portable TMS called DeepWiTraffic based on COTs WiFi devices and deep learning is proposed. DeepWiTraffic enables accurate vehicle detection and classification by exploiting the unique WiFi Channel State Information (CSI) of passing vehicles. Spatial and temporal correlations of preprocessed CSI amplitude and phase data are identified and analyzed using deep learning to classify vehicles into five different types: motorcycle, passenger vehicle, SUV, pickup truck, and large truck. A large amount of CSI data of passing vehicles and the corresponding ground truth video data are collected for about 120 hours to validate the effectiveness of DeepWiTraffic. The results show that the average detection accuracy of 99.4%, and the average classification accuracy of 91.1% (Motorcycle: 97.2%, Passenger Car: 91.1%, SUV:83.8%, Pickup Truck: 83.3%, and Large Truck: 99.7%) are achieved at a very small cost of about $1,000.

show abstract

“…In order to effectively overcome the lack of distinguishability of a single sensor, data fusion is employed to make full use of the complementary information between multi-source images (Hong et al, 2019c). Existing multi-source data-based methods (Marmanis et al, 2016;Niessner et al, 2017;Hendrik et al, 2018) use pre-fusion or post-fusion multiple sensor data under a supervised framework to improve the network's ability in feature learning rather than assisting in object detection. The main purpose of this paper is to realize vehicles auto-labeling to improve detection performance.…”

Section: Introductionmentioning

confidence: 99%

Vehicle detection of multi-source remote sensing data using active fine-tuning network

Hong

et al. 2020

ISPRS Journal of Photogrammetry and Remote Sensing

View full text Add to dashboard Cite

This is a pre-print of a paper accepted by ISPRS Journal Photogrammetry and Remote Sensing. Please note that compared to the published version, we corrected several F1-Scores in Tables (marked in red) due to miscalculation. Vehicle detection in remote sensing images has attracted increasing interest in recent years. However, its detection ability is limited due to lack of well-annotated samples, especially in densely crowded scenes. Furthermore, since a list of remotely sensed data sources is available, efficient exploitation of useful information from multi-source data for better vehicle detection is challenging. To solve the above issues, a multi-source active fine-tuning vehicle detection (Ms-AFt) framework is proposed, which integrates transfer learning, segmentation, and active classification into a unified framework for auto-labeling and detection. The proposed Ms-AFt employs a fine-tuning network to firstly generate a vehicle training set from an unlabeled dataset. To cope with the diversity of vehicle categories, a multi-source based segmentation branch is then designed to construct additional candidate object sets. The separation of high quality vehicles is realized by a designed attentive classifications network. Finally, all three branches are combined to achieve vehicle detection. Extensive experimental results conducted on two open ISPRS benchmark datasets, namely the Vaihingen village and Potsdam city datasets, demonstrate the superiority and effectiveness of the proposed Ms-AFt for vehicle detection. In addition, the generalization ability of Ms-AFt in dense remote sensing scenes is further verified on stereo aerial imagery of a large camping site.

show abstract

Investigations on the Potential of Convolutional Neural Networks for Vehicle Classification Based on RGB and Lidar Data

Cited by 9 publications

References 30 publications

Extraction of Pluvial Flood Relevant Volunteered Geographic Information (VGI) by Deep Learning from User Generated Texts and Photos

Extraction of Pluvial Flood Relevant Volunteered Geographic Information (VGI) by Deep Learning from User Generated Texts and Photos

DeepWiTraffic: Low Cost WiFi-Based Traffic Monitoring System Using Deep Learning

Vehicle detection of multi-source remote sensing data using active fine-tuning network

Contact Info

Product

Resources

About