Improving Depth Estimation by Embedding Semantic Segmentation: A Hybrid CNN Model

Valdez-Rodríguez, José E.; Calvo, Hiram; Felipe-Riveron, Edgardo M.; Moreno-Armendáriz, Marco A.

doi:10.3390/s22041669

Cited by 13 publications

(8 citation statements)

References 30 publications

(32 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, a class of CNN model is proposed, which is driven by RMB. Compared with the traditional model, it can better limit the expansion of the radius of the MEB, and increase the classi cation range between different types of image features, and nally promote CNN to obtain higher quality image features [11]. The literature uses minimum class classi cation variance SVM combined with Fisher linear discriminant theory to guide the deep learning of CNN, and proposes a CNN model combined with mcvsvm model.…”

Section: Relevant Workmentioning

confidence: 99%

RETRACTED ARTICLE: System simulation of computer image recognition technology application by using improved neural network algorithm

Wang

2023

Soft Comput

View full text Add to dashboard Cite

Digital image technology is penetrating into various elds of people's life, and it has been very mature and can effectively store and transmit data. Moreover, there are still various researches on image recognition, the core of this technology. The algorithm is mainly based on computer technology to obtain the target image for different scene categories, thus completely replacing the traditional classi cation form. Because of the limitations of traditional identi cation technology, there are some problems in the actual use. It does not depend on the prior knowledge requirements and can carry out complex feature space division. In this paper, an image recognition computer system is established by introducing an improved neural network algorithm. The algorithm is designed and tested, and the results show it has lower image recognition error rate. Through the computer image recognition technology design system test,it is found that the recognition accuracy is higher than the AlexNet model under four real environment conditions, which indicates that the improved and optimized model has better classi cation and recognition effect, the image recognition system designed in this paper can play an effective effect in practical application. By introducing the improved neural network algorithm into this eld, this paper designs an image recognition algorithm with better effect.

show abstract

Section: Relevant Workmentioning

confidence: 99%

RETRACTED ARTICLE: System simulation of computer image recognition technology application by using improved neural network algorithm

Wang

2023

Soft Comput

View full text Add to dashboard Cite

show abstract

“…For future research, further studies on different depth estimates are needed to apply and compare with the current model in terms of complexity and time. There are potential studies that have shown promising results, e.g., single-stage refinement CNN [26], embedding semantic segmentation by using a hybrid CNN model [27] for depth estimation. In addition, future research could explore the appropriateness of data augmentation in our case, which is consistent with exploring datasets that are more conducive to the research topic.…”

Section: Discussionmentioning

confidence: 99%

Depth Estimation for Egocentric Rehabilitation Monitoring Using Deep Learning Algorithms

et al. 2022

View full text Add to dashboard Cite

Upper limb impairment is one of the most common problems for people with neurological disabilities, affecting their activity, quality of life (QOL), and independence. Objective assessment of upper limb performance is a promising way to help patients with neurological upper limb disorders. By using wearable sensors, such as an egocentric camera, it is possible to monitor and objectively assess patients’ actual performance in activities of daily life (ADLs). We analyzed the possibility of using Deep Learning models for depth estimation based on a single RGB image to allow the monitoring of patients with 2D (RGB) cameras. We conducted experiments placing objects at different distances from the camera and varying the lighting conditions to evaluate the performance of the depth estimation provided by two deep learning models (MiDaS & Alhashim). Finally, we integrated the best performing model for depth-estimation (MiDaS) with other Deep Learning models for hand (MediaPipe) and object detection (YOLO) and evaluated the system in a task of hand-object interaction. Our tests showed that our final system has a 78% performance in detecting interactions, while the reference performance using a 3D (depth) camera is 84%.

show abstract

“…In 2018, Chen et al [6] proposed the DeeplabV3+ segmentation model, which combines the encoding-decoding structure with ASPP, and introduces dilated convolution to expand the receptive field of the model, thereby enhancing the ability of the model to segment targets of different sizes. Valdez-Rodríguez et al [15] combined the advantages of semantic segmentation to obtain local information with the depth estimation method, and used a mixed dataset for training. A 2D-3D hybrid CNN network is proposed, which can estimate the depth of a single image and segment the objects found in it.…”

Section: A Semantic Segmentationmentioning

confidence: 99%

A Novel Method for Road Anomaly Objects Detection in the Traffic Environment With Multi-Mechanism Fusion

Ci,

Xuan,

Lin

et al. 2024

IEEE Access

View full text Add to dashboard Cite

In the modern automotive industry, Advanced Driving Assistance Systems (ADAS) have gradually become a standard feature in various types of vehicles, with the important function of detecting road anomalies. The appearance of anomalies on the road can be attributed to unexpected situations while driving, and the current methods for detecting distant or small anomalies are not highly accurate. Therefore, in this paper, a method is proposed that uses semantic segmentation to extract key features from the image, and obtaining a new synthesized image by image resynthesis. Then, segmentation uncertainty and depth information are used to compare the differences between multiple feature maps and the input image to highlight the anomalies. Additionally, a postprocessor is designed to use an anomaly score to enhance the recognition of anomaly target and reduce false positives caused by noise. Experiments are conducted on the RoadObsta-cle21 dataset and the Lost and Found dataset, and various methods for detecting anomaly objects are compared. The experimental results demonstrate that the method proposed in this paper can effectively detect uncommon objects in the training dataset in road anomaly object detection. It improves the detection rate and reduces the false positive rate based on previous anomaly detection methods. The proposed method presented in this paper achieves high detection rates for both seen and unseen anomaly objects in the training set, which enhances the generalization ability of anomaly detection in the road area of interest.

show abstract

Improving Depth Estimation by Embedding Semantic Segmentation: A Hybrid CNN Model

Cited by 13 publications

References 30 publications

RETRACTED ARTICLE: System simulation of computer image recognition technology application by using improved neural network algorithm

RETRACTED ARTICLE: System simulation of computer image recognition technology application by using improved neural network algorithm

Depth Estimation for Egocentric Rehabilitation Monitoring Using Deep Learning Algorithms

A Novel Method for Road Anomaly Objects Detection in the Traffic Environment With Multi-Mechanism Fusion

Contact Info

Product

Resources

About