Towards Multi-View Object Class Detection

Alexander, Thomas; Ferrar, V.; Leibe, Bastian; Tuytelaars, Tinne; Schiel, B.; Gool, Luc Van

doi:10.1109/cvpr.2006.311

Cited by 172 publications

(180 citation statements)

References 20 publications

Supporting

Mentioning

177

Contrasting

Unclassified

Order By: Relevance

“…The canonical parts are regions containing multiple features in the images, and are the building blocks of the model. As previous research has shown, a part based representation [26,28,29] is more stable for capturing the appearance variability across instances of objects. A critical property introduced in [1] is that the canonical part retains the appearance of a region that is viewed most frontally on the object.…”

Section: Overview Of the Savarese Et Al Model [1]mentioning

confidence: 86%

See 1 more Smart Citation

View Synthesis for Recognizing Unseen Poses of Object Classes

Savarese

2008

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. An important task in object recognition is to enable algorithms to categorize objects under arbitrary poses in a cluttered 3D world. A recent paper by has proposed a novel representation to model 3D object classes. In this representation stable parts of objects from one class are linked together to capture both the appearance and shape properties of the object class. We propose to extend this framework and improve the ability of the model to recognize poses that have not been seen in training. Inspired by works in single object view synthesis (e.g., Seitz & Dyer [2]), our new representation allows the model to synthesize novel views of an object class at recognition time. This mechanism is incorporated in a novel two-step algorithm that is able to classify objects under arbitrary and/or unseen poses. We compare our results on pose categorization with the model and dataset presented in [1]. In a second experiment, we collect a new, more challenging dataset of 8 object classes from crawling the web. In both experiments, our model shows competitive performances compared to [1] for classifying objects in unseen poses.

show abstract

Section: Overview Of the Savarese Et Al Model [1]mentioning

confidence: 86%

“…Recently, a number of works have proposed interesting solutions for capturing the multi-view essence of an object category [1,27,28,29,30,31,32]. These techniques bridge the gap between models that represent an object category from just a single 2D view and models that represent single object instances from multiple views.…”

Section: Introductionmentioning

confidence: 99%

View Synthesis for Recognizing Unseen Poses of Object Classes

Savarese

2008

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…However, many models have only been demonstrated to work with data sets restricted to canonical views of categories. Thomas et al (2006) try to overcome this limitation by training several pose-specific implicit shape models (ISM) (Leibe et al, 2004) for each category. After the training of these ISMs, detected parts from neighboring pose-dependent ISMs are associated by so-called "activation links".…”

Section: Visual Category Learning Approachesmentioning

confidence: 99%

A life-long learning vector quantization approach for interactive learning of multiple categories

et al. 2012

View full text Add to dashboard Cite

We present a new method capable of learning multiple categories in an interactive and lifelong learning fashion to approach the "stability-plasticity dilemma". The problem of incremental learning of multiple categories is still largely unsolved. This is especially true for the domain of cognitive robotics, requiring real-time and interactive learning. To achieve the life-long learning ability for a cognitive system, we propose a new learning vector quantization approach combined with a category-specific feature selection method to allow several metrical "views" on the representation space of each individual vector quantization node. These category-specific features are incrementally collected during the learning process, so that a balance between the correction of wrong representations and the stability of acquired knowledge is achieved. We demonstrate our approach for a difficult visual categorization task, where the learning is applied for several complex-shaped objects rotated in depth.

show abstract

“…Recent approaches of this type include [13,17,23]. While 2D singleview object detection methods can be used to addressed the task by combining the outputs of classifiers trained for different object views, such approaches are argued to be only effective when there are sufficient single-view detectors to cover all possible viewpoints [13].…”

Section: Related Workmentioning

confidence: 99%

“…Ferrari et al [12] proposed a method to compute feature tracks densely connecting multiple model views of a single object. In [13], Implicit Shape Model [14] and [12] are combined, and activation links for transferring votes across views are used to address the object detection from arbitrary viewpoints. propose a compact model of an object by linking together diagnostic parts of the objects from different viewpoints.…”

Section: Related Workmentioning

confidence: 99%

View-Invariant Object Detection by Matching 3D Contours

Meng

Latecki

2013

Computer Vision - ACCV 2012 Workshops

View full text Add to dashboard Cite

Abstract. We propose an approach for view-invariant object detection directly in 3D with following properties: (i) The detection is based on matching of 3D contours to 3D object models. (ii) The matching is constrained with qualitative spatial relations such as above/below, left/right, and front/back. (iii) In order to ensure that any matching solution satisfies these constraints, we formulate the matching problem as finding maximum weight subgraphs with hard constraints, and utilize a novel inference framework to solve this problem. Given a single view of an RGB-D camera, we obtain 3D contours by "back projecting" 2D contours extracted in the depth map. As our experimental results demonstrate, the proposed approach significantly outperforms the state-of-the-art 2D approaches, in particular, latent SVM object detector, as well as recently proposed approaches for object detection in RGB-D data.

show abstract

Towards Multi-View Object Class Detection

Cited by 172 publications

References 20 publications

View Synthesis for Recognizing Unseen Poses of Object Classes

View Synthesis for Recognizing Unseen Poses of Object Classes

A life-long learning vector quantization approach for interactive learning of multiple categories

View-Invariant Object Detection by Matching 3D Contours

Contact Info

Product

Resources

About