Small Object Detection with Multiscale Features

Hu, Guoxiong; Hu, Lei; Huang, Li; Han, Jiaming

doi:10.1155/2018/4546896

Cited by 56 publications

(41 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general, the object detection model detects objects using features extracted through the backbone network, and VGGNet, ResNet, and DenseNet are mainly used as the backbone networks [37][38][39][40]. When VGGNet or ResNet is used as a backbone network, features of several layers are often fused to detect small objects [10,41]. However, DenseNet utilizes all of the features from the previous layer in each layer, it was found that the process of selecting a layer for feature fusion could be In general, the object detection model detects objects using features extracted through the backbone network, and VGGNet, ResNet, and DenseNet are mainly used as the backbone networks [37][38][39][40].…”

Section: Training and Validation Methodsmentioning

confidence: 99%

“…However, DenseNet utilizes all of the features from the previous layer in each layer, it was found that the process of selecting a layer for feature fusion could be In general, the object detection model detects objects using features extracted through the backbone network, and VGGNet, ResNet, and DenseNet are mainly used as the backbone networks [37][38][39][40]. When VGGNet or ResNet is used as a backbone network, features of several layers are often fused to detect small objects [10,41]. However, DenseNet utilizes all of the features from the previous layer in each layer, it was found that the process of selecting a layer for feature fusion could be omitted and the features of the ships could be better extracted.…”

Section: Training and Validation Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Ship Detection from X-Band SAR Images Using M2Det Deep Learning Model

2020

View full text Add to dashboard Cite

Synthetic aperture radar (SAR) images have been used in many studies for ship detection because they can be captured without being affected by time and weather. In recent years, the development of deep learning techniques has facilitated studies on ship detection in SAR images using deep learning techniques. However, because the noise from SAR images can negatively affect the learning of the deep learning model, it is necessary to reduce the noise through preprocessing. In this study, deep learning vessel detection was performed using preprocessed SAR images, and the effects of the preprocessing of the images on deep learning vessel detection were compared and analyzed. Through the preprocessing of SAR images, (1) intensity images, (2) decibel images, and (3) intensity difference and texture images were generated. The M2Det object detection model was used for the deep learning process and preprocessed SAR images. After the object detection model was trained, ship detection was performed using test images. The test results are presented in terms of precision, recall, and average precision (AP), which were 93.18%, 91.11%, and 89.78% for the intensity images, respectively, 94.16%, 94.16%, and 92.34% for the decibel images, respectively, and 97.40%, 94.94%, and 95.55% for the intensity difference and texture images, respectively. From the results, it can be found that the preprocessing of the SAR images can facilitate the deep learning process and improve the ship detection performance. The results of this study are expected to contribute to the development of deep learning-based ship detection techniques in SAR images in the future.

show abstract

Section: Training and Validation Methodsmentioning

confidence: 99%

Section: Training and Validation Methodsmentioning

confidence: 99%

Ship Detection from X-Band SAR Images Using M2Det Deep Learning Model

2020

View full text Add to dashboard Cite

show abstract

“…Conventional object detection (OD) methods are not suitable to detect small objects, because they use very deep depth networks with pooling operations for feature extraction [46,47,48,49,50]. For example, Faster-RCNN employs anchor boxes to extract object candidate regions from a feature map.…”

Section: Proposed Traffic Light Recognition Methodsmentioning

confidence: 99%

Traffic Light Recognition Based on Binary Semantic Segmentation Network

Kim

Yoo

Park

et al. 2019

Sensors

View full text Add to dashboard Cite

A traffic light recognition system is a very important building block in an advanced driving assistance system and an autonomous vehicle system. In this paper, we propose a two-staged deep-learning-based traffic light recognition method that consists of a pixel-wise semantic segmentation technique and a novel fully convolutional network. For candidate detection, we employ a binary-semantic segmentation network that is suitable for detecting small objects such as traffic lights. Connected components labeling with an eight-connected neighborhood is applied to obtain bounding boxes of candidate regions, instead of the computationally demanding region proposal and regression processes of conventional methods. A fully convolutional network including a convolution layer with three filters of (1 × 1) at the beginning is designed and implemented for traffic light classification, as traffic lights have only a set number of colors. The simulation results show that the proposed traffic light recognition method outperforms the conventional two-staged object detection method in terms of recognition performance, and remarkably reduces the computational complexity and hardware requirements. This framework can be a useful network design guideline for the detection and recognition of small objects, including traffic lights.

show abstract

“…The discriminator, however, competes with the generator to identify the representation generated by the generator and allows the generator to have a representation that is useful for detection. Hu et al [36] proposed a way to use the features extracted from other levels of features. Bosquet et al [37] proposed the problem of a loss of target information as existing detector networks undergo downsampling.…”

Section: Related Workmentioning

confidence: 99%

Heterogeneous Gray-Temperature Fusion-Based Deep Learning Architecture for Far Infrared Small Target Detection

Ryu

Kim

2019

Journal of Sensors

View full text Add to dashboard Cite

This paper proposes the end-to-end detection of a deep network for far infrared small target detection. The problem of detecting small targets has been a subject of research for decades and has been applied mainly in the field of surveillance. Traditional methods focus on filter design for each environment, and several steps are needed to obtain the final detection result. Most of them work well in a given environment but are vulnerable to severe clutter or environmental changes. This paper proposes a novel deep learning-based far infrared small target detection method and a heterogeneous data fusion method to solve the lack of semantic information due to the small target size. Heterogeneous data consists of radiometric temperature data (14-bit) and gray scale data (8-bit), which includes the physical meaning of the target, and compares the effects of the normalization method to fuse heterogeneous data. Experiments were conducted using an infrared small target dataset built directly on the cloud backgrounds. The experimental results showed that there is a significant difference in performance according to the various fusion methods and normalization methods, and the proposed detector showed approximately 20% improvement in average precision (AP) compared to the baseline constant false alarm rate (CFAR) detector.

show abstract

Small Object Detection with Multiscale Features

Cited by 56 publications

References 25 publications

Ship Detection from X-Band SAR Images Using M2Det Deep Learning Model

Ship Detection from X-Band SAR Images Using M2Det Deep Learning Model

Traffic Light Recognition Based on Binary Semantic Segmentation Network

Heterogeneous Gray-Temperature Fusion-Based Deep Learning Architecture for Far Infrared Small Target Detection

Contact Info

Product

Resources

About