TOD-CNN: An Effective Convolutional Neural Network for Tiny Object Detection in Sperm Videos

04/18/2022

∙

The detection of tiny objects in microscopic videos is a problematic point, especially in large-scale experiments. For tiny objects (such as sperms) in microscopic videos, current detection methods face challenges in fuzzy, irregular, and precise positioning of objects. In contrast, we present a convolutional neural network for tiny object detection (TOD-CNN) with an underlying data set of high-quality sperm microscopic videos (111 videos, > 278,000 annotated objects), and a graphical user interface (GUI) is designed to employ and test the proposed model effectively. TOD-CNN is highly accurate, achieving 85.60% AP_50 in the task of real-time sperm detection in microscopic videos. To demonstrate the importance of sperm detection technology in sperm quality analysis, we carry out relevant sperm quality evaluation metrics and compare them with the diagnosis results from medical doctors.

READ FULL TEXT

TOD-CNN: An Effective Convolutional Neural Network for Tiny Object Detection in Sperm Videos

T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos

LCDet: Low-Complexity Fully-Convolutional Neural Networks for Object Detection in Embedded Systems

Object Detection During Newborn Resuscitation Activities

Probabilistic Model of Object Detection Based on Convolutional Neural Network

An Efficient Approach for Polyps Detection in Endoscopic Videos Based on Faster R-CNN

Obstruction level detection of sewer videos using convolutional neural networks

Adversarially robust deepfake media detection using fused convolutional neural network predictions

TOD-CNN: An Effective Convolutional Neural Network for Tiny Object Detection in Sperm Videos

Related Research

T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos

LCDet: Low-Complexity Fully-Convolutional Neural Networks for Object Detection in Embedded Systems

Object Detection During Newborn Resuscitation Activities

Probabilistic Model of Object Detection Based on Convolutional Neural Network

An Efficient Approach for Polyps Detection in Endoscopic Videos Based on Faster R-CNN

Obstruction level detection of sewer videos using convolutional neural networks

Adversarially robust deepfake media detection using fused convolutional neural network predictions