Compound Exemplar Based Object Detection by Incremental Random Forest

Abstract

This paper describes a new hybrid detection method that combines exemplar based approach with discriminative patch selection. More specifically, we applied a modified random forest for retrieval of input similar local patches of stored exemplars while rejecting background patches. A recursive algorithm based on dynamic programming 2D matching optimization is applied after the aforementioned patch retrieving stage in order to enforce geometric constraints of object patches. Our proposed approach demonstrates experimentally that it performs well while maintaining the capability for incremental learning.

Reflection Invariance: an important consideration of image orientation

“…The Hough space encodes the hypothesis h(c, x, s) for an object belonging to class c ∈ C centred on x ∈ R D and with size s. The term cuboid refers to a local image patch (D = 2) or video spatio-temporal neighborhood (D = 3) depending on the task. Since their introduction in 2009 [12], Hough Forests have gained some interest in object detection tasks [13,14]. Features are extracted from feature channels derived from an image, and are used to cast votes in Hough space.…”

Partial Transfer Ensemble Learning Framework: A Method for Intelligent Diagnosis of Rotating Machinery Based on an Incomplete Source Domain

“…Intelligent fault diagnosis has received a lot of attention in recent years from both industrial engineers and academic researchers and has accomplished remarkable achievements [ 5 ]. For example, shallow machine learning techniques such as support vector machine (SVM) [ 6 ] and random forest (RF) [ 7 ] have been studied. Deep learning methods have been researched that can adaptively extract the fault features hidden in a collected signal, such as recurrent neural network (RNN) [ 8 ], convolutional neural network (CNN) [ 9 ], and stack autoencoder (SAE) [ 10 ].…”