A systematic review of object detection from images using deep learning

Kaur, Jaskirat; Singh, Williamjeet

doi:10.1007/s11042-023-15981-y

Cited by 18 publications

(2 citation statements)

References 362 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Extensive experiments are conducted on the TT100K dataset and notable improvement is achieved by our feature‐enhanced hybrid attention network (FEHAN) in terms of the trade‐off between accuracy and speed. Specifically, the state‐of‐the‐art models including SSD‐MobileNet [13], YOLOv4 [43], YOLOv5 [23], YOLOX [50], YOLOv6 [51], and YOLOv7 [52] are selected for the comparative experiments on detection accuracy, number of parameters, and computation overhead, as shown in Table 1.…”

Section: Experiments and Resultsmentioning

confidence: 99%

A feature‐enhanced hybrid attention network for traffic sign recognition in real scenes

He,

Lan,

Zhou

et al. 2024

IET Image Processing

View full text Add to dashboard Cite

Currently, traffic sign recognition techniques have been brought into the assistive driving of automobiles. However, small traffic sign recognition in real scenes is still a challenging task due to the class imbalance issue and the size limit of the traffic signs. To address the above issues, a feature‐enhanced hybrid attention network is proposed based on YOLOv5s for a small, fast, and accurate traffic sign detector. First, a series of online data augmentation strategies are designed in the preprocessing module for the model training. Second, the hybrid channel and spatial attention module CSAM are integrated into the backbone for a better feature extraction ability. Third, the channel attention module CAM is used in the detection head for a more efficient feature fusion ability. To validate the approach, extensive experiments are conducted based on the Tsinghua‐Tencent 100K dataset. It is found that the novel method achieves state‐of‐the‐art performance with only negligible increases in the model parameter and computational overhead. Specifically, the , parameters, and FLOPs are 85.8%, 7.13 M, and 16.1 G, respectively.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

A feature‐enhanced hybrid attention network for traffic sign recognition in real scenes

He,

Lan,

Zhou

et al. 2024

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…Image denoising, a fundamental task in computer vision [1][2][3][4], involves the restoration of clean images from noisy ones, thereby enhancing their quality. The effectiveness of denoising directly impacts various downstream tasks in computer vision applications, including super resolution [5][6][7], semantic segmentation [8][9][10], and object detection [11][12][13]. Moreover, denoising techniques play a crucial role in improving the image quality captured by diverse devices like mobile phones, reflecting the widespread demand in imaging domains.…”

Section: Introductionmentioning

confidence: 99%

A Dual-Branch Self-Boosting Network Based on Noise2Noise for Unsupervised Image Denoising

Geng,

Xu,

Xiong

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

While unsupervised denoising models have shown progress in recent years, their noise reduction capabilities still lag behind those of supervised denoising models. This limitation can be attributed to the lack of effective constraints during training, which only utilizes noisy images and hinders further performance improvements In this work, we propose a novel dual-branch self-boosting network called DBSNet, which offers a straightforward and effective approach to image denoising. By leveraging task-dependent features, we exploit the intrinsic relationships between the two branches to enhance the effectiveness of our proposed model. Initially, we extend the classic Noise2Noise (N2N) architecture by adding a new branch for noise component prediction to the existing single-branch network designed for content prediction. This expansion creates a dual-branch structure, enabling us to simultaneously decompose a given noisy image into its content (clean) and noise components. This enhancement allows us to establish stronger constraint conditions and construct more powerful loss functions to guide the training process. Furthermore, we replace the UNet structure in the N2N network with the proven DnCNN (Denoising Convolutional Neural Network) sequential network architecture, which enhances the nonlinear mapping capabilities of the DBSNet. This modification enables our dual-branch network to effectively map a noisy image to its content (clean) and noise components simultaneously. To further improve the stability and effectiveness of training, and consequently enhance the denoising performance, we introduce a feedback mechanism where the network’s outputs, i.e., content and noise components, are fed back into the dual-branch network. This results in an enhanced loss function that ensures our model possesses excellent decomposition ability and further boosts the denoising performance. Extensive experiments conducted on both synthetic and real-world images demonstrate that the proposed DBSNet outperforms the unsupervised N2N denoising model as well as mainstream supervised models trained with supervised methods. Moreover, the evaluation results on real-world noisy images highlight the desirable generalization ability of DBSNet for practical denoising applications.

show abstract

Entangled appearance and motion structures network for multi-object tracking and segmentation

Aryanfar,

Aliyari Shoorehdeli,

Seydi

2024

Machine Vision and Applications

View full text Add to dashboard Cite

The object segmentation mask’s observation sequence shows the trend of changes in the object’s observable geometric form, and predicting them may assist in solving various difficulties in multi-object tracking and segmentation (MOTS). With this aim, we propose the entangled appearance and motion structures network (EAMSN), which can predict the object segmentation mask at the pixel level by integrating VAE and LSTM. Regardless of the surroundings, each EAMSN keeps complete knowledge about the sequence of probable changes in the seen map of the object and its related dynamics. It suggests that EAMSN understands the item meaningfully and is not reliant on instructive examples. As a result, we propose a novel MOTS algorithm. By employing different EAMSNs for each kind of item and training them offline, ambiguities in the segmentation mask discovered for that object may be recovered, and precise estimation of the real boundaries of the object at each step. We analyze our tracker using the KITTI MOTS and MOTS challenges datasets, which comprise car and pedestrian objects, to illustrate the usefulness of the suggested technique. As a result, we developed distinct EAMSNs for cars and pedestrians, trained using the MODELNET40 and Human3.6 M datasets, respectively. The discrepancy between training and testing data demonstrates that EAMSN is not dependent on training data. Finally, we compared our strategy to a variety of other ways. Compared to the published findings, our technique gets the best overall performance.

show abstract

A systematic review of object detection from images using deep learning

Cited by 18 publications

References 362 publications

A feature‐enhanced hybrid attention network for traffic sign recognition in real scenes

A feature‐enhanced hybrid attention network for traffic sign recognition in real scenes

A Dual-Branch Self-Boosting Network Based on Noise2Noise for Unsupervised Image Denoising

Entangled appearance and motion structures network for multi-object tracking and segmentation

Contact Info

Product

Resources

About