The use of Deep learning techniques in the field of Marine Science has become popular in recent years. For instance, many works propose the application of instance segmentation neural networks (in particular, Mask R-CNN) for detection and classification of fish in underwater images. The performance of these learning-based approaches depends heavily on the volume of data used for training, which, in the case of instance segmentation models for fish detection, implies that human experts must label and mark the shapes of all the fish appearing in a vast amount of underwater images. This is an enormously time-consuming task that we seek to alleviate in this paper. We propose a training strategy that combines manual and semi-automatic annotations. The latter are obtained in a weakly-supervised manner: the bounding box that contains the fish is manually selected, but its shape is automatically obtained thanks to a pretrained encoder-decoder segmentation network. Several popular architectures for this encoder-decoder network are examined. This strategy permits to reduce drastically the annotation cost for instance segmentation, at the expense of a small drop in performance with respect to the use of fully manual annotations. We show that a balance can be achieved between the segmentation performance and the time used to collect the training data by using the proposed strategy.

Leveraging Bounding Box Annotations for Fish Segmentation in Underwater Images

Deep reinforcement learning for autonomous driving in uncontrolled intersections of Indian roads

We present a cost-effective testbed and advanced software architecture suitable for ADAS applications, which utilizes an onboard GPU for high-performance processing. By implementing an optimized parallel processing method, this innovative architecture can collect and synchronize multi-sensor data, such as camera and radar, with high precision. The software architecture dynamically allocates processing power to each data processing sub-module based on the utilized sensor hardware and optimizes the data flow accordingly. With the aid of parallel processing, the system can effectively reduce the time delay during data acquisition. Indoor and road stereo-camera and dual-radar data acquisition results are presented. Post-processing of the data includes the creation of disparity map depth images and combined radar point clouds identifying departing and approaching vehicles and objects.

A synchronous multi-modal data acquisition and processing system for ADAS applications using an onboard GPU

Robustness against distribution shifts is crucial for object detection models in real-world applications. In this study, we evaluate the performance of four state-of-the-art models against natural perturbations, retrain them with synthetic perturbations using the AugLy augmentation package, and assess their improved performance against natural perturbations. Our empirical ablation study focuses on the brightness perturbation modality using the COCO 2017 and ExDARK datasets. Our findings suggest that synthetic perturbations can effectively improve model robustness against real-world distribution shifts, providing valuable insights for deploying robust object detection models in real-world scenarios. 

Shedding Light on Darkness: Enhancing Object Detection Robustness with Synthetic Perturbations for Real-world Challenges

Advanced CNN Approach for Segmentation of Diseased Areas in Plant Images

Lane detection techniques for self-driving vehicle: comprehensive review

Self-driving cars or vehicles don’t require humans to take control to safely operate the vehicle. Also, popular as autonomous or driverless cars, they combine various sensors and software like radar, lidar, sonar, GPS, odometry, etc. to control, navigate, and drive the vehicle. This chapter presents the working model of the Self-driving Car: Lane detection and Collision prevention system (LDCP System) using machine learning and computer vision. In the LDCP System two processes working simultaneously based on object detection and recognition and human facial expression recognition to hold the responsibility of the car’s outer and inner environment to prevent any collision which occurs due to human errors such as lack of concentration or focus. The extraction of information about objects and face(s) is performed by capturing the live video feed through multiple cameras. The implemented algorithm is advanced enough to works in real-time which is for sure can prevent any collisions. 

Self-driving Car: Lane Detection and Collision Prevention System

This chapter presents the efficient working model of the Advance Collision Prevention System (ACP System) using computer vision and machine learning (ML). The facial expression detection technique is widely used in the recognition of facial expression to understand human intention. In this chapter, we capture the driver’s face in real-time and process every frame to detect the drowsy and yawn expression to determine whether the driver is feeling sleepy or not using computer vision. Simultaneously we apply a machine-learning algorithm to detect if the driver is using a cell phone while driving. The proposed algorithm works in day and night both and makes the system (ACP System) more advance and highly efficient to prevent any such collisions which may occur due to human error like lack of concentration while driving. 

Advance Collision Prevention System

AbstractThe COVID-19 Pandemic is considered as the worst situation for human beings; it affected people’s lives worldwide. Due to this pandemic, the respective government authority announced the lockdown to break the coronavirus chain. The lockdown impacted people’s mental health, leading to many psychological issues as well as hampered students’ academics. In this chapter we have studied the impacts on students’ academics due to lockdown effect. The data has been collected via a google form questionnaire circulated to various educational institutes. Further, we have developed a novel machine learning classifier model called Naïve Bayes-Support Vector Machine for analyzing the data, which utilizes the properties of both classifiers by using a deep learning framework. We have used natural language processing (TextBlob, Stanza and Vader) libraries to label the dataset and applied in the proposed NBSVM method and other machine learning models and classified the sentiments into two categories (Positive vs Negative). We also applied the natural language processing libraries used a topic-modelling technique called Latent Dirichlet Allocation to know the essential topics words of both classes from students’ feedback data. The study revealed 83% and 86% accuracy for unigram and bigram, respectively, whereas the precision was 79% and recall 81%. According to NLP libraries’ result, approximately 71% of the feedback’s sentiment is negative, and only 16% of feedbacks are positive. The proposed model shown that (Naïve Bayes-Support Vector Machine) outperforms the other variants of the Naïve Bayes and support vector machine.KeywordsCOVID-19Machine learningNaïve BayesNatural language processingSentiment analysisSupport vector machine 

A Novel Machine Learning Classification Model to Analyze the COVID-19 Pandemic's Impact on Academics: Sentiment Analysis Approach

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Prashant Singh

Author Tools

Chat about Author

Papers

Lane detection techniques for self-driving vehicle: comprehensive review

Self-driving Car: Lane Detection and Collision Prevention System

Advance Collision Prevention System

A Novel Machine Learning Classification Model to Analyze the COVID-19 Pandemic's Impact on Academics: Sentiment Analysis Approach