IMORL: Incremental Multiple-Object Recognition and Localization

Abstract

This paper proposes an incremental multiple-object recognition and localization (IMORL) method. The objective of IMORL is to adaptively learn multiple interesting objects in an image. Unlike the conventional multiple-object learning algorithms, the proposed method can automatically and adaptively learn from continuous video streams over the entire learning life. This kind of incremental learning capability enables the proposed approach to accumulate experience and use such knowledge to benefit future learning and the decision making process. Furthermore, IMORL can effectively handle variations in the number of instances in each data chunk over the learning life. Another important aspect analyzed in this paper is the concept drifting issue. In multiple-object learning scenarios, it is a common phenomenon that new interesting objects may be introduced during the learning life. To handle this situation, IMORL uses an adaptive learning principle to autonomously adjust to such new information. The proposed approach is independent of the base learning models, such as decision tree, neural networks, support vector machines, and others, which provide the flexibility of using this method as a general learning methodology in multiple-object learning scenarios. In this paper, we use a neural network with a multilayer perceptron (MLP) structure as the base learning model and test the performance of this method in various video stream data sets. Simulation results show the effectiveness of this method.

Towards lifelong assistive robotics: A tight coupling between object perception and manipulation

“…This leads to several shortcomings such as the inability to detect/recognize new or unknown categories. To cope with these issues, several cognitive robotics groups have started to explore how robots could learn incrementally from their own experiences as well as from interaction with humans [8][9] [10].…”

“…In these approaches, the set of classes is predefined and the models of known object categories are enhanced (e.g., augmented, improved) over time, while in open-ended approaches the set of categories is also continuously growing. Haibo et al [10] proposed an incremental multiple-object recognition and localization (IMORL) framework using a multilayer perceptron (MLP) structure as the base learning model. The authors claimed that the proposed framework can incrementally learn from accumulated experiences and use such knowledge for object recognition.…”

Biologically Motivated Novel Localization Paradigm by High‐Level Multiple Object Recognition in Panoramic Images

“…According to recent works, dense and redundant low level features can be reduced by the unsupervised clustering-based feature selection [ 16 ]. He and Chen proposed an incremental multiple object learning, recognition, and localization using a multilayer perceptron [ 17 ]. Although it is an adaptive object learning framework and works well for an input video stream, it can only localize objects in 2D image space.…”