A framework for visual-context-aware object detection in still images

Perko, Roland; Leonardis, Aleš

doi:10.1016/j.cviu.2010.03.005

Cited by 27 publications

(32 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Perko and Leonardis (2010) compared the contribution of object cooccurrence, geometric cues (expressed as ground, vertical structure and sky presence maps), texture cues (anisotropy, polarity, and texture contrast maps) and their combination. They found that texture was better than geometry and object cooccurrence and that combining all the cues outperformed each single one.…”

Section: Please Scroll Down For Articlementioning

confidence: 99%

Influence of the amount of context learned for improving object classification when simultaneously learning object and contextual cues

Marat¹,

Itti²

2012

Visual Cognition

View full text Add to dashboard Cite

Section: Please Scroll Down For Articlementioning

confidence: 99%

Influence of the amount of context learned for improving object classification when simultaneously learning object and contextual cues

Marat¹,

Itti²

2012

Visual Cognition

View full text Add to dashboard Cite

“…However, the extent to which such a network is able to incorporate context is still not entirely understood [23]. To improve both types of detectors, many works have sought to explicitly combine their results with contextual reasoning to strengthen detections that appear in favorable context and to weaken detections that do not (among others, see [9,2,20,16,25,32,31,6,24,8,30,26,18,1]).…”

Section: Introductionmentioning

confidence: 99%

Exploring the Bounds of the Utility of Context for Object Detection

Barnea

Ben-Shahar

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

The recurring context in which objects appear holds valuable information that can be employed to predict their existence. This intuitive observation indeed led many researchers to endow appearance-based detectors with explicit reasoning about context. The underlying thesis suggests that stronger contextual relations would facilitate greater improvements in detection capacity. In practice, however, the observed improvement in many cases is modest at best, and often only marginal. In this work we seek to improve our understanding of this phenomenon, in part by pursuing an opposite approach. Instead of attempting to improve detection scores by employing context, we treat the utility of context as an optimization problem: to what extent can detection scores be improved by considering context or any other kind of additional information? With this approach we explore the bounds on improvement by using contextual relations between objects and provide a tool for identifying the most helpful ones. We show that simple cooccurrence relations can often provide large gains, while in other cases a significant improvement is simply impossible or impractical with either co-occurrence or more precise spatial relations. To better understand these results we then analyze the ability of context to handle different types of false detections, revealing that tested contextual information cannot ameliorate localization errors, severely limiting its gains. These and additional insights further our understanding on where and why utilization of context for object detection succeeds and fails.

show abstract

“…The task of object detection entails the analysis of an image for the identification of all instances of objects from predefined categories [7,11]. While most methods employ local information, in particular the appearance of individual objects [5], the contextual relations between objects were also shown to be a valuable source of information [23,26]. Thus, the challenge is to combine the local appearance at each image location with information regarding the other objects or detections.…”

Section: Introductionmentioning

confidence: 99%

Contextual Object Detection with a Few Relevant Neighbors

Barnea

Ben-Shahar

2019

Computer Vision – ACCV 2018

View full text Add to dashboard Cite

A natural way to improve the detection of objects is to consider the contextual constraints imposed by the detection of additional objects in a given scene. In this work, we exploit the spatial relations between objects in order to improve detection capacity, as well as analyze various properties of the contextual object detection problem. To precisely calculate context-based probabilities of objects, we developed a model that examines the interactions between objects in an exact probabilistic setting, in contrast to previous methods that typically utilize approximations based on pairwise interactions. Such a scheme is facilitated by the realistic assumption that the existence of an object in any given location is influenced by only few informative locations in space. Based on this assumption, we suggest a method for identifying these relevant locations and integrating them into a mostly exact calculation of probability based on their raw detector responses. This scheme is shown to improve detection results and provides unique insights about the process of contextual inference for object detection. We show that it is generally difficult to learn that a particular object reduces the probability of another, and that in cases when the context and detector strongly disagree this learning becomes virtually impossible for the purposes of improving the results of an object detector. Finally, we demonstrate improved detection results through use of our approach as applied to the PASCAL VOC and COCO datasets.

show abstract

A framework for visual-context-aware object detection in still images

Cited by 27 publications

References 47 publications

Influence of the amount of context learned for improving object classification when simultaneously learning object and contextual cues

Influence of the amount of context learned for improving object classification when simultaneously learning object and contextual cues

Exploring the Bounds of the Utility of Context for Object Detection

Contextual Object Detection with a Few Relevant Neighbors

Contact Info

Product

Resources

About