Multi-Class Objects Detection Method in Remote Sensing Image Based on Direct Feedback Control for Convolutional Neural Network

Cheng, Bei; Li, Zhengzhou; Wu, Qingqing; Li, Bo; Yang, Heng; Lin, Qing; Qi, Bo

doi:10.1109/access.2019.2943346

Cited by 7 publications

(3 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also compared the proposed PTAN framework with other five object detectors including RICNN [21], R-P-Faster RCNN [15], CBFF-SSD [28], MIF-CNN [29] and DFCCNN-VGG [30]. These methods were proposed for remote sensing image object detection.…”

Section: E Ablation Experiments On the Nwpu Vhr-10 Datasetmentioning

confidence: 99%

Patch-Based Three-Stage Aggregation Network for Object Detection in High Resolution Remote Sensing Images

Sui¹,

Meng

Gao³

2020

IEEE Access

View full text Add to dashboard Cite

High-resolution remote sensing image object detection plays an increasingly important role in image processing and interpretation. The application of region-based convolutional neural network (R-CNN) greatly enhances the performance of object detection. However, the attributes of remote sensing images such as overlarge image size, similar background, disequilibrium distribution of categories make this task more challenging. The previous works have focused on extracting multi-scale features of region proposals, often ignoring the quality of region of interest (ROI). In this work, we proposed a patch-based three-stage aggregation network (PTAN) for object detection in high-resolution remote sensing images. It consists of a three-stage cascade structure that sequentially improves the quality of candidate regions by increasing the IoU threshold stage by stage, and adopts a resampling strategy to obtain sufficient region proposals. At the same time, we also proposed patch-based strategy and applied it to the framework during training and inference. Ablation experiments and comprehensive evaluations on a communal remote sensing image object detection dataset DOTA demonstrate the effectiveness and robustness of the proposed framework, which obtained a mean average precision (mAP) value of 0.7958 on validation dataset and a front-rank mAP of 0.7858 on testing dataset. On another remote sensing image object detection dataset NWPU VHR-10, the proposed PTAN obtained a mAP value of 0.9187, outperforming other five object detectors.

show abstract

Section: E Ablation Experiments On the Nwpu Vhr-10 Datasetmentioning

confidence: 99%

Patch-Based Three-Stage Aggregation Network for Object Detection in High Resolution Remote Sensing Images

Sui¹,

Meng

Gao³

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Regarding the machine learning approach [12], object detection can be achieved by developing a classifier for a variety of texture features, including SR-based features (sparse representation) [13], scale-invariant feature transformation (SIFT) [14], bag-ofwords (BOW) feature [16], Histogram of Oriented Gradients (HOG) [15] and hair-like features [17]. The classifier can typically be trained using a variety of methods, including knearest neighbors (kNN), AdaBoost, Support Vector Machines (SVM), Sparse Representation Based Classification (SRC), Conditional Random Fields (CRF) and many others [18]. In some cases, the machine learning-based technique performs better than the alternatives, but choosing hand-built features and training data would significantly impact how well it performed.…”

Section: Introductionmentioning

confidence: 99%

Performance Analysis of Different Optimization Algorithms for Multi-Class Object Detection

Borade

Muddana

2023

IJRITCC

View full text Add to dashboard Cite

Object recognition is a significant approach employed for recognizing suitable objects from the image. Various improvements, particularly in computer vision, are probable to diagnose highly difficult tasks with the assistance of local feature detection methodologies. Detecting multi-class objects is quite challenging, and many existing researches have worked to enhance the overall accuracy. But because of certain limitations like higher network loss, degraded training ability, improper consideration of features, less convergent and so on. The proposed research introduced a hybrid convolutional neural network (H-CNN) approach to overcome these drawbacks. The collected input images are pre-processed initially through Gaussian filtering to eradicate the noise and enhance the image quality. Followed by image pre-processing, the objects present in the images are localized using Grid Guided Localization (GGL). The effective features are extracted from the localized objects using the AlexNet model. Different objects are classified by replacing the concluding softmax layer of AlexNet with Support Vector Regression (SVR) model. The losses present in the network model are optimized using the Improved Grey Wolf (IGW) optimization procedure. The performances of the proposed model are analyzed using PYTHON. Various datasets are employed, including MIT-67, PASCAL VOC2010, Microsoft (MS)-COCO and MSRC. The performances are analyzed by varying the loss optimization algorithms like improved Particle Swarm Optimization (IPSO), improved Genetic Algorithm (IGA), and improved dragon fly algorithm (IDFA), improved simulated annealing algorithm (ISAA) and improved bacterial foraging algorithm (IBFA), to choose the best algorithm. The proposed accuracy outcomes are attained as PASCAL VOC2010 (95.04%), MIT-67 dataset (96.02%), MSRC (97.37%), and MS COCO (94.53%), respectively.

show abstract

“…Gong et al [6] introduced an object detection model that enriches feature representation and adopts the basic context information between objects. Cheng et al [7] proposed a multiclass object detection feedback network (MODFN) using a top-down feedback mechanism based on a ISPRS Int. J. Geo-Inf.…”

Section: Introductionmentioning

confidence: 99%

Weighted Ensemble Object Detection with Optimized Coefficients for Remote Sensing Images

Körez

Barışçı

Çetin

et al. 2020

IJGI

View full text Add to dashboard Cite

The detection of objects in very high-resolution (VHR) remote sensing images has become increasingly popular with the enhancement of remote sensing technologies. High-resolution images from aircrafts or satellites contain highly detailed and mixed backgrounds that decrease the success of object detection in remote sensing images. In this study, a model that performs weighted ensemble object detection using optimized coefficients is proposed. This model uses the outputs of three different object detection models trained on the same dataset. The model’s structure takes two or more object detection methods as its input and provides an output with an optimized coefficient-weighted ensemble. The Northwestern Polytechnical University Very High Resolution 10 (NWPU-VHR10) and Remote Sensing Object Detection (RSOD) datasets were used to measure the object detection success of the proposed model. Our experiments reveal that the proposed model improved the Mean Average Precision (mAP) performance by 0.78%–16.5% compared to stand-alone models and presents better mean average precision than other state-of-the-art methods (3.55% higher on the NWPU-VHR-10 dataset and 1.49% higher when using the RSOD dataset).

show abstract

Multi-Class Objects Detection Method in Remote Sensing Image Based on Direct Feedback Control for Convolutional Neural Network

Cited by 7 publications

References 69 publications

Patch-Based Three-Stage Aggregation Network for Object Detection in High Resolution Remote Sensing Images

Patch-Based Three-Stage Aggregation Network for Object Detection in High Resolution Remote Sensing Images

Performance Analysis of Different Optimization Algorithms for Multi-Class Object Detection

Weighted Ensemble Object Detection with Optimized Coefficients for Remote Sensing Images

Contact Info

Product

Resources

About