Video analytics faces complex challenges in object detection and classification. Deep learning based approaches have achieved remarkable success in past decade. However, existing object identification models that utilize backbone’s core features still present challenges due to their lack of semantic information. To address these issues, a novel object detection and classification framework utilizing Batch normalization and Softswish activation adapted ResNet (BS2ResNet) and Logistic Tanh Kaiming Bi-directional Long Short Term Memory (LTK-Bi-LSTM) techniques was proposed. The framework employs frame conversion, noise removal, and contrast elevation during frame pre-processing, followed by background subtraction using the Supreme Distance-centered Fuzzy C-Means (SD-FCM) clustering algorithm, and edge detection using the Hyperbolic Tangent Kernel Canny Edge Detector (HTKCED). BS2ResNet is then used for object detection, and features are extracted and passed to the LTK-Bi-LSTM neural network for object classification. The proposed system was found to improve object detection and classification accuracy, outperforming existing techniques.

A Multiple moving object detection, tracking, and counting algorithm is mainly designed exclusively suitable for congested areas. The counting system can alleviate the betrayal performance in the crowded areas. Most of the existing methods developed for tracking and counting face serious challenges in detection due to high densities of the target. This condition urged the researchers to update the existing systems. The present methodology was designed to address such issues. In the present methodology, the contrast was initially enhanced between the objects and their backgrounds using a Double Plateau Histogram Equalization (DPHE). Then, the motion was estimated for the contrast-enhanced image to identify the moment of the object using the modified Adaptive Distance Covariance Rood Pattern Search (ADCRPS) algorithm. After that, the morphological operation was deployed to sharpen the images by removing all the unwanted things. Then, the features were extracted and important features were selected using the modified Chaotic Tent Shuffled Shepherd Optimization (CTSSO) Algorithm. With the selected features object, detection was done using the proposed Scaled Non-Monotonic Cauchy Dense Convolutional Neural Network (SNMC-DenCNN). The detected object was then tracked with the aid of Channel and Spatial Reliability Tracker (CSRT). Finally, the objects were counted by intersection over union (IOU) by explicitly computing the association between detected and tracked objects. Also, the experimental results showed the effectiveness and efficiency of the proposed system with enhanced accuracy.

Rice being crucial for sustaining over half of the global population, is recognized as one of the foremost plants in agriculture worldwide. The presence of diseases affecting rice plants can significantly influence both the quantity and quality of the harvest, sometimes resulting in crop losses ranging from 30 to 60%. This work focuses on automating the recognition and categorization of common rice leaf diseases using deep learning, particularly with respect to the DenseNet architecture. Preprocessing methods, the deployment of DenseNet for disease diagnosis, and the gathering of an extensive dataset are all part of this work. The efficacy of the model is demonstrated by the high recall, accuracy, and precision rates of the experimental data. This work presents the effectiveness of DenseNet, explores the implications of the results for precision agriculture, and identifies future directions for deep learning-based plant disease detection research

An efficient model to detect and track the objects in adverse weather is proposed using Tanh Softmax (TSM) EfficientDet and Jaccard Similarity based Kuhn-Munkres (JS-KM) with Pearson-Retinex in this paper. The noises were initially removed using Differential Log Energy Entropy adapted Wiener Filter (DLE-WF). The Log Energy Entropy value was calculated between the pixels instead of calculating the local mean of a pixel in the normal Wiener filter. Also, the segmentation technique was carried out using Fringe Binarization adapted K-Means Algorithm (FBKMA). The movement of segmented objects was detected using the optical flow technique, in which the optical flow was computed using the Horn-Schunck algorithm. After motion estimation, the final step in the proposed system is object tracking. The motion-estimated objects were treated as the target that is initially in the first frame. The target was tracked by JS-KM algorithm in the subsequent frame. At last, the experiential evaluation is conducted to confirm the proposed model’s efficacy. The outcomes of Detection in Adverse Weather Nature (DAWN) dataset proved that in comparison to the prevailing models, a better performance was achieved by the proposed methodology.

One of the most significant issues in surveillance videos is the detection of vehicles and objects at real time. Adverse weather conditions and lighting (illumination) variations are a few of the challenges faced while detecting objects through surveillance videos. In this work, a You Only Look Once v4 model, combined with a Spatial Pyramid Pooling and a Path Aggregation Network block and a contrast enhancement framework for effective detection of objects with higher accuracy is proposed. The video is converted to frames and is completely enhanced throughout using the Exposure Fusion Network. The brightness of the frames is equalized such that every point in the frame is clearly visible to the naked eye. Finally, the objects in the frames are detected using a YOLOv4 model, which is coupled with a SPP layer and a PAN network. The model generates an accuracy of 92.6%.

Object detection and classification are the trending research topics in the field of computer vision because of their applications like visual surveillance. However, the vision-based objects detection and classification methods still suffer from detecting smaller objects and dense objects in the complex dynamic environment with high accuracy and precision. The present paper proposes a novel enhanced method to detect and classify objects using Hyperbolic Tangent based You Only Look Once V4 with a Modified Manta-Ray Foraging Optimization-based Convolution Neural Network. Initially, in the pre-processing, the video data was converted into image sequences and Polynomial Adaptive Edge was applied to preserve the Algorithm method for image resizing and noise removal. The noiseless resized image sequences contrast was enhanced using Contrast Limited Adaptive Edge Preserving Algorithm. And, with the contrast-enhanced image sequences, the Hyperbolic Tangent based You Only Look Once V4 was trained for object detection. Additionally, to detect smaller objects with high accuracy, Grasp configuration was observed for every detected object. Finally, the Modified Manta-Ray Foraging Optimization-based Convolution Neural Network method was carried out for the detection and the classification of objects. Comparative experiments were conducted on various benchmark datasets and methods that showed improved accurate detection and classification results.

Precise traffic flow prediction is essential for efficient traffic management and improving transportation systems. This paper proposes a novel approach for long-term traffic flow prediction using spatio-temporal data analysis. The method utilizes a combined Deep Residual Network with BiLSTM network to effectively capture intricate temporal and spatial dependencies within the data. This approach leverages the respective strengths of Residual Networks and BiLSTM networks. The proposed model is evaluated on the PEMS dataset, a publicly available highway database in California, USA, and compared with existing traffic flow prediction models such as RNN, CNN, LSTM, GRU, CNN with BiLSTM, and ResNet with BiLSTM. The outcomes clearly indicate that the proposed model surpasses all other models in both mean absolute error (MAE) and root mean square error (RMSE).The proposed Deep Residual Network with BiLSTM network achieves an MAE of 2.36 and an RMSE of 3.47, indicating its superior performance for long-term traffic movement prediction. This paper illustrates the effectiveness of the proposed method for traffic movement prediction using spatio-temporal data analysis and has significant practical implications for traffic management and transportation planning.

Unmanned Ariel Vehicle (UAV) s are dealing with several safety and protection issues including internal hardware/software and potential attacks. In addition, detecting UAV anomalies will be a crucial responsibility to defend against hostile enemies and prevent accidents. In this research, we present a UAV and an Automatic Dependent (AD) system using surveillance and Machine Learning (ML) algorithms to analyze data from their detectors in real-time. Proposed Improved Region based Convolutional Neural Network (IRCNN) model used to generate and acquire the characteristics of untreated sensor information and characteristics to facilitate AD. The proposed model creating an Inertial Measurement Unit (IMU) & UAV sensors dataset using cyber security simulation system and Active Learning (AL) identifies aggressions based on the least probable interrogation method. This proposed model enables the identification to efficiently improve the occurrences of unexplained aggressions discovered of IRCNN at reduced labeling cost. A thorough trial showed that IRCNN-AL is effective at detecting unknown threats with frequency improvements of between 9% and 30% on comparison approaches. The AL methodology presented with as few as 1% of a labeled unexpected aggressions.

In this digital era, digital documents are widely used. The merits of digital documents are huge while its security and privacy are at large. Hence Cryptography is used to secure digital documents. Cryptography is a method of storing and transmitting data in a particular form so that only those for whom it is intended can read and process it. In this paper a novel idea is proposed, digital documents are encrypted using 256 bit cryptographic key which is generated by multimodal biometric system. This system uses Palmprint and Fingerprint as traits. The features of both traits were extracted and fused at feature level. This biometric based cryptographic key is unpredictable to an intruder as the intruder lacks the knowledge of physical traits of the user. By this proposed model confidentiality, integrity, availability mechanisms are achieved. This biometric based cryptographic security can be integrated to e-governance and e-health for efficient management.

To improve the security of medical data and also transfer the medical images and their information among, the radiologist and physicians for concerning is termed as Teleradiology. Maintaining a secure environment is a challenging for Teleradiology from various issues like malpractice liability and Image Retention etc. To overcome these issues and also to maintain secure transformation of medical data, we propose a combined novel system using Biometrics, encryption and watermarking method termed as, "An Iris Based Reversible Watermarking for the security of Teleradiology. Here, we use CIA mechanism for medical information and also for medical image transformation. Enrollment and Embedding process is carried out for the addition of user's and their information. Verification and Extraction process is carried out for the authentication of information identity.

Multimodal biometrics is an evolving technology in the fields of security. Biometrics system reduces the effort of remember a memorable password. Multimodal biometrics system uses two or more traits for efficient recognition. In this paper, a novel idea is proposed by combining IRIS and Finger knuckle print for recognition. The texture pattern present in IRIS and Finger Knuckle print are distinct when combining both the patterns will become highly distinctive. The two traits were captured using sensors and the features were extracted using Haar Wavelet for IRIS and Linear Discriminant Analysis for Finger Knuckle Print. Both the extracted features were fused at score level. The experimental results has been observed in terms of False Acceptance Rate, False Rejection Rate, Genuine Acceptance Rate and Total Error Rate.

The Completely Automated Public Turing test to tell Computers and Humans Apart (CAPTCHA) is used to believe that a human is using the web service [1].For the online services which are been provided in web services is been abused by automated bots over the internet.So CAPTCHA is used as a protection from these malicious programs for web security.But the bots are intelligent enough to break through these CAPTCHA.To increase the security, there are several CAPTCHA techniques has been proposed.In this paper various types of CAPTCHA techniques has been discussed and more secure techniques for the bot protection were discussed.

Super resolution is a technique which is used to enhance the visual quality of a sequence of low resolution image by constructing a single high resolution image. This paper is interested in acquiring the automatic number plate recognition system from the traffic surveillance video. The proposed system detects the number plate of a vehicle from video input and then performs the super resolution technique. Applying the Optical Character Recognition Technique it acquires the text from the super resolution image of vehicle number plate by means it compares with the RTO database and then it display the details of the vehicle such as owners name, vehicle registration etc.

Multimodal biometrics system becomes an inexorable trend in future. Multimodal biometrics overcomes many drawbacks over unimodal biometrics. Some of the drawbacks are nonuniversality, noisy data and spoof attack. Multimodal biometric is more efficient and accurate than unimodal system. In this paper we present a multimodal biometric recognition system using Iris and finger Inner-knuckle print. This system will give excellent result over performance.