Object Detection with Convolutional Context Features

Date

2017-01-01

Author

Kaya, Emre Can
Alatan, Abdullah Aydın

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

267
views

0
downloads

A novel extension to Huh B-ESA object detection algorithm is proposed in order to learn convolutional context features for determining boundaries of objects better. For input images, the hypothesis windows and their context around those windows are learned through convolutional layers as two parallel networks. The resulting object and context feature maps are combined in such a way that they preserve their spatial relationship. The proposed algorithm is trained and evaluated on PASCAL VOC 2007 detection benchmark dataset and yielded improvements in performance over state-of-the-art, for almost all classes, especially the ones with distinctive context.

Subject Keywords

CNN region proposal network, Object detection, Human detection, Context, Deep learning

URI

https://hdl.handle.net/11511/32884

DOI

https://doi.org/10.1109/siu.2017.7960502

Collections

Department of Electrical and Electronics Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

IMPROVING PROPOSAL-BASED OBJECT DETECTION USING CONVOLUTIONAL CONTEXT FEATURES Kaya, Emre Can; Alatan, Abdullah Aydın (2018-10-10) A novel extension to proposal-based detection is proposed in order to learn convolutional context features for determining boundaries of objects better. Objects and their context are aimed to be learned through parallel convolutional stages. The resulting object and context feature maps are combined in such a way that they preserve their spatial relationship. The proposed algorithm is trained and evaluated on PASCAL VOC 2007 detection benchmark dataset and yielded improvements in performance over baseline, ...
Rescoring detections based on contextual scores in object detection Zorlu, Ersan Vural; Akbaş, Emre; Department of Computer Engineering (2019) To detect objects in an image, current state-of-the-art object detectors firstly definecandidate object locations, and then classify each of them into one of the predefinedcategories or as background. They do so by using the visual features extracted locallyfrom the candidate locations; omitting the rich contextual information embedded inthe whole image. Contextual information can be utilized to complement the informa-tion extracted locally and thereby to improve object detection accuracy. Researchershave p...
Topological Navigation Algorithm Design and Analysis Using Spherical Images Şahin, Yasin; Koku, Ahmet Buğra; Department of Mechanical Engineering (2022-8-23) A topological navigation algorithm that has the capability of mapping and localization based on visual contents is proposed. Keypoint detection and feature matching are conducted on spherical images to extract significant features among sequential frames. Robot movement direction is estimated based on historical angle differences of significant features to reach the final destination. The navigation process is supported with visual egocentric localization to gain simultaneous localization and mapping compet...
OBJECT LOCALIZATION WITHOUT BOUNDING BOX INFORMATION USING GENERATIVE ADVERSARIAL REINFORCEMENT LEARNING Halici, Eren; Alatan, Abdullah Aydın (2018-10-10) Object localization can be defined as the task of finding the bounding boxes of objects in a scene. Most of the state-of-the-art approaches utilize meticulously handcrafted training datasets. In this work, we are aiming to create a generative adversarial reinforcement learning framework, which can work without having any explicit bounding box information. Instead of relying on bounding boxes, our framework uses tightly cropped object images as training data. Our image localization framework consists of two ...
Utilization of dense depth information for monoview object detection and instance segmentation Çakırgöz, Çağlayan Can; Alatan, Abdullah Aydın; Department of Electrical and Electronics Engineering (2022-5-10) Object detection aims for detecting objects of certain classes in an image by bounding them in rectangular boxes whereas instance segmentation tries to detect objects in pixel level. Deep learning techniques, which have shown great improvements over the last decade, are utilized in these topics as well, and a significant success is achieved against the traditional methods. Similar improvements can be observed in dense depth estimation which deals with deducing dense information of a scene from a single imag...

Citation Formats

E. C. Kaya and A. A. Alatan, “Object Detection with Convolutional Context Features,” 2017, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/32884.