A real-time surveillance mini-rover based on OpenCV-Python-JAVA using Raspberry Pi 2

Hossain, Nazmul; Kabir, Mohammad Tanzir; Rahman, Tarif Riyad; Hossen, Mohamed Sajjad; Salauddin, Fahim

doi:10.1109/iccsce.2015.7482232

Cited by 10 publications

(4 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most importantly, it is open-source hardware with programmable computing language like Python and scratch under the Linux platform. The study [15] chose Raspberry Pi 2 as a computing module. Raspberry Pi is having the role of video compression.…”

Section: Related Workmentioning

confidence: 99%

Enabling of Technology in Preventing Vandalism in Tower Communication

2020

IJATCSE

View full text Add to dashboard Cite

The theft of telecommunication tower supporting devices or commonly known as Base Transceiver Station (BTS), continues to increase every year, as reported by digital media viva.co.id from several operators who stated that they found significant losses from the theft. Reported by the daily Republika.co.id, in 2013, Telkomsel operators claimed to have lost up to Three billion rupiahs more due to the theft of BTS batteries in only a few districts and cities in South Sulawesi. Therefore it is necessary to evaluate the method of using technology to prevent damage. The vandalism prevention system can design by utilizing the Internet of Things (IoT) technology. The design uses a Raspberry Pi computing module, which is accompanied by a GSM transmission module to send a response signal to the motion captured by the camera. Photos are sent to the server, in this case, the Telegram Bot

show abstract

Section: Related Workmentioning

confidence: 99%

Enabling of Technology in Preventing Vandalism in Tower Communication

2020

IJATCSE

View full text Add to dashboard Cite

show abstract

“…A number of papers used python and raspberry pi for security or intruder detection where python library openCV is used for image analysis [21,22].Raspberry can also be used for communication intensive works. It's used for cloud based works [23]. That drives us to make our virtual bot in raspberry-pi microcomputer.…”

Section: Chapter II Literature Reviewmentioning

confidence: 99%

Embedded System based Bangla Intelligent Social Virtual Robot with Sentiment Analysis

Hossain

Banik

et al. 2018

2018 Joint 7th International Conference on Informatics, Electronics &Amp; Vision (ICIEV) and 2018 2nd International Conference

View full text Add to dashboard Cite

Bangla is the mother tongue of millions of people all over the world.Despite of being a very popular language, any social virtual robot that can intelligently communicate in Bangla is a fairytale till now. One of the main reason of this is lack of rich text corpus and previous research on Bangla language. The proposed Bangla Intelligent Social Virtual Robot can communicate in Bangla intelligently and can express its reflective emotion virtually with the help of machine learning algorithms and sentiment analysis.In this paper we discuss the approached system, design methodology and implementation details of first ever Bangla virtual embedded robot followed by the methodology of building a rich Bangla text corpus. The proposed embedded virtual robot turns out better performer when compared with only known Bangla intelligent chatbot named 'Golpo' and the embedded system performance efficiency has been upgraded with the help CPU over-clocking technique v ACKNOWLEDGEMENTWe would like to express our sincere gratitude to The Most Merciful Allah who blessed us with patience, determination, ability and opportunity to complete the research work within time.We would love to thank from the core of our heart to our supervisor Dr. Amitabha Chakrabarty who has accepted us to do thesis under his supervision and has helped us to complete it within time with his valuable guidance and advises. We are fortunate and grateful to be able to work under his supervision.We are grateful to the online based group "Vasha Shainik" who have helped us translating English subtitles and providing all of their work till now in order to build the first ever Bangla text corpus. Without these dedicated, hardworking and patriot soul, the long cherished Bangla Corpus still would have remained a dream. Moreover, we are under obligation of Dr. Ashraful Alam for providing us utmost support and his credit card to that helped us bearing the expenses of this virtual robot.Finally, we are grateful to all of our family members and faculty members of Department of Computer Science and Engineering, BRAC University for believing in our ability and for supporting and encouraging us through thick and thin. vi

show abstract

“…Most of the existing research uses toy cars as research subjects. For example, Hossain et al [1] used toy cars for experiments. However, because it was a toy car, there were reproduction errors such as speed deviation during turning which would occur in each experiment.…”

Section: Introductionmentioning

confidence: 99%

Multi-task Autonomous Driving Based on Improved Convolutional Neural Network and ST Loss in MTS and MOD Modes

Nie¹,

Jian²

2022

Curr. Appl. Sci. Technol.

View full text Add to dashboard Cite

Multi-task autonomous driving is a research hotspot in autonomous driving. However, existing research has only achieved single-task or dual-task autonomous driving. Therefore, we propose two novel multi-task approaches: a multi-task shared model mode (MTS) and a multi-object dual-model mode (MOD). In addition, existing neural network architectures are underperforming in multi-task autonomous driving, so we propose a novel neural network architecture - MT-ResNet26. Moreover, to alleviate the problem of noise and class imbalance from data, we propose a new loss function - Stable Loss (ST Loss). Finally, our smart car can achieve multi-task road tracking, left-right turn sign recognition, automatic obstacle avoidance, stop, real-time acceleration and deceleration. In addition, we compare the existing multi-task autonomous driving model YS-VGG17_MSE, which shows our MT-ResNet26_ST is superior in loss value and actual performance. Meanwhile, we use our proposed approaches to train two classical neural networks—ResNet18_MSE* and DenseNet121_MSE*, so that they also achieve multi-task autonomous driving with our proposed approaches, showing the applicability of MTS and MOD. Furthermore, we compare MT-ResNet26_MSE with MT-ResNet26_ST, and the results show that the model using our novel ST Loss outperforms the model using the original loss function MSE. To sum up, it is shown that the performance of multi-task autonomous driving can be achieved and improved using our proposed neural network architecture and loss function. Furthermore, we propose optimized multi-task modes. OMTS and OMOD optimize and accelerate the models using semi-precision techniques based on the TensorRT. The results show that the optimized multi-task autonomous driving accuracy has been further improved.

show abstract

A real-time surveillance mini-rover based on OpenCV-Python-JAVA using Raspberry Pi 2

Cited by 10 publications

References 3 publications

Enabling of Technology in Preventing Vandalism in Tower Communication

Enabling of Technology in Preventing Vandalism in Tower Communication

Embedded System based Bangla Intelligent Social Virtual Robot with Sentiment Analysis

Multi-task Autonomous Driving Based on Improved Convolutional Neural Network and ST Loss in MTS and MOD Modes

Contact Info

Product

Resources

About