K
Koyel Banerjee
Researcher at BMW
Publications - 9
Citations - 150
Koyel Banerjee is an academic researcher from BMW. The author has contributed to research in topics: Object detection & Convolutional neural network. The author has an hindex of 5, co-authored 8 publications receiving 106 citations. Previous affiliations of Koyel Banerjee include Missouri University of Science and Technology.
Papers
More filters
Journal ArticleDOI
Nuclei-Based Features for Uterine Cervical Cancer Histology Image Analysis With Fusion-Based Classification
Peng Guo,Koyel Banerjee,R. Joe Stanley,Rodney Long,Sameer Antani,George R. Thoma,Rosemary E. Zuna,Shelliane R. Frazier,Randy Hays Moss,William V. Stoecker +9 more
TL;DR: Novel acellular and atypical cell concentration features computed from vertical segment partitions of the epithelium region within digitized histology images to quantize the relative increase in nuclei numbers as the CIN grade increases are introduced.
Proceedings ArticleDOI
Online Camera LiDAR Fusion and Object Detection on Hybrid Data for Autonomous Driving
TL;DR: This study improves the LiDAR and camera fusion approach of Levinson and Thrun by relying on intensity discontinuities and erosion and dilation of the edge image for increased robustness against shadows and visual patterns, which is a recurring problem in point cloud related work.
Journal ArticleDOI
Enhancements in localized classification for uterine cervical cancer digital histology image assessment
Peng Guo,Haidar Almubarak,Koyel Banerjee,R. Joe Stanley,L. Rodney Long,Sameer Antani,George R. Thoma,Rosemary E. Zuna,Shelliane R. Frazier,Randy Hays Moss,William V. Stoecker +10 more
TL;DR: Individual vertical segment CIN classification accuracy improvement is reported using the logistic regression classifier for an expanded data set of 118 histology images and the Logistic and Random Tree classifiers outperformed the benchmark SVM and LDA classifiers from previous research.
Patent
System and Method for Estimating Vehicular Motion Based on Monocular Video Data
Ludmila Levkova,Koyel Banerjee +1 more
TL;DR: In this paper, a pre-trained convolutional neural network is used to estimate vehicle movement based on monocular video data, and a vehicle movement parameter such as ego-speed is estimated using real-time images captured by a single camera.
Proceedings ArticleDOI
Velocity estimation from monocular video for automotive applications using convolutional neural networks
TL;DR: This work modifications their synchrony autoencoder method to achieve a ”real time” performance in a wide variety of driving environments, which led to a model which is 1.5 times faster and uses only half of the total memory by comparison with the original.