Evaluation of Transfer Learning Techniques for Classification and Localization of Marine Animals

被引：0

作者：

Singh, Parmeet ^{[1
]}

Seto, Mae ^{[2
]}

机构：

[1] Dalhousie Univ, Fac Comp Sci, Halifax, NS, Canada

[2] Dalhousie Univ, Dept Mech Engn, Halifax, NS, Canada

来源：

VISAPP: PROCEEDINGS OF THE 14TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS, VOL 4 | 2019年

关键词：

Convolution Neural Networks; Ensemble Learning; Marine Animals; VGG; Inception; Computer Vision; Bounding Boxes; SHAPE; FISH; LENGTH;

D O I：

10.5220/0007390201690176

中图分类号：

TP31 [计算机软件];

学科分类号：

081202 ; 0835 ;

摘要：

The objective is to evaluate methods for simultaneous classification and localization towards a better size estimate of marine animals in still images. Marine animals in such images vary in orientations and size. It is challenging to create a bounding box that predicts the shape of the object. We compare axis-aligned and rotatable bounding box techniques for size estimation.

引用

页码：169 / 176

页数：8

共 22 条

[1]

Aleju, 2015, AL IMG

[2]

[Anonymous], 2017, LEARNING ROTATION IN

[3]

[Anonymous], 2016, IEEE C COMP VIS PATT

[4] LEARNING LONG-TERM DEPENDENCIES WITH GRADIENT DESCENT IS DIFFICULT [J].