Much effort has been applied to research on object detection by statistical learning methods in recent years, and the results of that work are expected to find use in fields such as ITS and security. Up to now, the research has included optimization of computational algorithms for real-time processing on hardware such as GPU's and FPGAs. Such optimization most often works only with particular parameters, which often forfeits the flexibility that comes with dynamic changing of the target object. We propose a hardware architecture for faster detection and flexible target reconfiguration while maintaining detection accuracy. Tests confirm operation in a practical time when implemented in an FPGA board.

Machine learning is used in various fields and demand for implementations is increasing. Within machine learning, a Random Forest is a multi-class classifier with high-performance classification, achieved using bagging and feature selection, and is capable of high-speed training and classification. However, as a type of ensemble learning, Random Forest determines classifications using the majority of multiple trees; so many decision trees must be built. Performance increases with the number of decision trees, requiring memory, and decreases if the number of decision trees is decreased. Because of this, the algorithm is not well suited to implementation on small-scale hardware as an embedded system. As such, we have proposed Boosted Random Forest, which introduces a boosting algorithm into the Random Forest learning method to produce high-performance decision trees that are smaller. When evaluated using databases from the UCI Machine learning Repository, Boosted Random Forest achieved performance as good or better than ordinary Random Forest, while able to reduce memory use by 47%. Thus, it is suitable for implementing Random Forests on embedded hardware with limited memory.

Pedestrian attribute information is important function for an advanced driver assistance system (ADAS). Pedestrian attributes such as body pose, face orientation and open umbrella indicate the intended action or state of the pedestrian. Generally, this information is recognized using independent classifiers for each task. Performing all of these separate tasks is too time-consuming at the testing stage. In addition, the processing time increases with increasing number of tasks. To address this problem, multi-task learning or heterogeneous learning is performed to train a single classifier to perform multiple tasks. In particular, heterogeneous learning is able to simultaneously train a classifier to perform regression and recognition tasks, which reduces both training and testing time. However, heterogeneous learning tends to result in a lower accuracy rate for classes with few training samples. In this paper, we propose a method to improve the performance of heterogeneous learning for such classes. We introduce a rarity rate based on the importance and class probability of each task. The appropriate rarity rate is assigned to each training sample. Thus, the samples in a mini-batch for training a deep convolutional neural network are augmented according to this rarity rate to focus on the classes with a few samples. Our heterogeneous learning approach with the rarity rate performs pedestrian attribute recognition better, especially for classes representing few training samples.