Sequential Architecture for Efficient Car Detection

2007 ◽  
Author(s):  
Zhenfeng Zhu ◽  
Yao Zhao ◽  
Hanqing Lu
Keyword(s):  
Car Detection

Stereo priori RCNN based car detection on point level for autonomous driving

2021 ◽  
pp. 107346
Author(s):  
Chongben Tao ◽  
Haotian He ◽  
Fenglei Xu ◽  
Jiecheng Cao
Keyword(s):  
Autonomous Driving ◽  
Car Detection ◽  
Point Level

scholarly journals Car detection and classification using cascade model

2018 ◽  
Vol 12 (10) ◽  
pp. 1201-1209 ◽  
Author(s):  
Jun Liang ◽  
Xu Chen ◽  
Mei-ling He ◽  
Long Chen ◽  
Tao Cai ◽  
...  
Keyword(s):  
Cascade Model ◽  
Car Detection

scholarly journals A Novel Traffic Tracking System Based on division of Video into Frames and Processing

2013 ◽  
pp. 255-259
Author(s):  
Prabhakar Telagarapu ◽  
B. Jagdishwar Rao ◽  
J. Venkata Suman ◽  
K. Chiranjeevi
Keyword(s):  
Tracking System ◽  
Relative Size ◽  
Morphological Processing ◽  
Binary Image ◽  
Video Frame ◽  
Gray Scale ◽  
Binary Images ◽  
Morphological Image Processing ◽  
Car Detection ◽  
Analysis Technique

The objective of this paper is to visualize and analyze video.Videos are sequence of image frames. In this work, algorithm will be developed to analyze a frame and the same will be applied to all frames in a video. It is expected see unwanted objects in video frame, which can be removed by converting colour frames into a gray scale and implement thresh holding algorithm on an image. Threshold can be set depending on the object to be detected. Gray scale image will be converted to binary during thresh holding process. To reduce noise, to improve the robustness of the system, and to reduce the error rate in detection and tracking process, morphological image processing method for binary images is used. Morphological processing will be applied on binary image to remove small unwanted objects that are presented in a frame. A developed blob analysis technique for extracted binary image facilitates pedestrian and car detection. Processing blob’s information of relative size and location leads to distinguishing between pedestrian and car. The threshold, morphological and blobs process is applied to all frames in a video and finally original video with tagged cars will be displayed.

scholarly journals Image-Based Surrogates of Socio-Economic Status in Urban Neighborhoods Using Deep Multiple Instance Learning

2018 ◽  
Vol 4 (11) ◽  
pp. 125 ◽  
Author(s):  
Christos Diou ◽  
Pantelis Lelekas ◽  
Anastasios Delopoulos
Keyword(s):  
Local Level ◽  
Multiple Instance Learning ◽  
Training Data ◽  
Percentage Error ◽  
Socioeconomic Indicators ◽  
Google Street View ◽  
Surrogate Variable ◽  
Car Detection ◽  
Street View ◽  
Surrogate Variables

(1) Background: Evidence-based policymaking requires data about the local population’s socioeconomic status (SES) at detailed geographical level, however, such information is often not available, or is too expensive to acquire. Researchers have proposed solutions to estimate SES indicators by analyzing Google Street View images, however, these methods are also resource-intensive, since they require large volumes of manually labeled training data. (2) Methods: We propose a methodology for automatically computing surrogate variables of SES indicators using street images of parked cars and deep multiple instance learning. Our approach does not require any manually created labels, apart from data already available by statistical authorities, while the entire pipeline for image acquisition, parked car detection, car classification, and surrogate variable computation is fully automated. The proposed surrogate variables are then used in linear regression models to estimate the target SES indicators. (3) Results: We implement and evaluate a model based on the proposed surrogate variable at 30 municipalities of varying SES in Greece. Our model has R 2 = 0 . 76 and a correlation coefficient of 0 . 874 with the true unemployment rate, while it achieves a mean absolute percentage error of 0 . 089 and mean absolute error of 1 . 87 on a held-out test set. Similar results are also obtained for other socioeconomic indicators, related to education level and occupational prestige. (4) Conclusions: The proposed methodology can be used to estimate SES indicators at the local level automatically, using images of parked cars detected via Google Street View, without the need for any manual labeling effort.

scholarly journals 3D car-detection based on a Mobile Deep Sensor Fusion Model and real-scene applications

PLoS ONE ◽  
2020 ◽  
Vol 15 (9) ◽  
pp. e0236947
Author(s):  
Qiang Zhang ◽  
Xiaojian Hu ◽  
Ziyi Su ◽  
Zhihong Song
Keyword(s):  
Sensor Fusion ◽  
Fusion Model ◽  
Car Detection ◽  
Real Scene
Sign in / Sign up

Export Citation Format

Share Document