Robert Boschgmbh

Jayanta Kumar Dutta

Naveen Ramakrishnan

Stefan Weissert

Ravi Kumar Satzoda

Ryan Burt

Filipe Goncalves

Krishnan Bharath Navalpakkam

Alexander Hirsch

Yumi Kondo

Marc Naumann

Jiayi Liu

Mohak Shah

Chun-Hao Liu

Unmesh Kurup

Michael Erz

Luiz Ricardo Douat

Identifying key frames of a video for use in training a machine learning model is provided. Object detection is performed to identify frames of a video including target classes of objects of interest. Feature extraction is performed on the identified frames to generate raw feature vectors. The feature vectors are compressed into lower dimension vectors. The compressed feature vectors are compressed into a plurality of clusters. The clustered compressed feature vectors are filtered to identify the key frames from each of the plurality of clusters. The key frames may be provided as a representative data set of the video.

Automated key frame selection

A vehicle for collecting image data of a target object for generating a classifier. The vehicle includes an image sensor and an electronic processor. The electronic processor is configured to determine a plurality of potential trajectories of the vehicle, determine, for each of the plurality of potential trajectories of the vehicle, a total number of views including the target object that would be captured by the image sensor as the vehicle moved along the respective trajectory, and determine a key trajectory of the vehicle from the plurality of potential trajectories based on the total number of views including the target of the key trajectory.

Trajectory design for image data acquisition for object detection/recognition

A method and system are disclosed for monitoring passengers in within a cabin of a vehicle and determining whether the passengers are engaging in abnormal behavior. The method and system uses a novel vector to robustly and numerically represent the activity of the passengers in a respective frame, which is referred to herein as an 'activity vector.' Additionally, a Gaussian Mixture Model is utilized by the method and system to distinguish between normal and abnormal passenger behavior. Cluster components of the Gaussian Mixture Model are advantageously learned using an unsupervised approach in which training data is not labeled or annotated to indicate normal and abnormal passenger behavior. In this way, the Gaussian Mixture Model can be trained at a very low cost.

System and method for detecting abnormal passenger behavior in autonomous vehicles

A search framework for finding effective architectural building blocks for deep convolutional neural networks is disclosed. The search framework described herein utilizes a building block which incorporates branch and skip connections. At least some operations of the architecture of the building block are undefined and treated as hyperparameters which can be automatically selected and optimized for a particular task. The search framework uses random search over the reduced search space to generate a building block and repeats the building block multiple times to create a deep convolutional neural network.

Effective building block design for deep convolutional neural networks using search

Growing community of inventors

Sunnyvale, CA, United States of America

Jayanta Kumar Dutta