Electronics Projects on EFFICIENT RANKING AND RETRIEVAL OF VIDEO BASED ON HUMAN ACTIONS USING SPATIOTEMPORAL LOCALIZATION

June 12th, 2015 by admin | No Comments | Filed in 1000 Projects, 10000 Engineering Project Ideas, ELECTRONICS PROJECTS

PROJECT ABSTRACT

In this project we propose an efficient video searching and video retrieval of human actions using spatio-temporal localization algorithm. Content-based video retrieval(CBVR) which is an extension of content-based image retrieval(CBIR).Highly efficient localization model that first performs temporal localization based on histograms of evenly spaced time-slices, then spatial localization based on histograms of a 2D- spatial grid. In the existing method they used dollar detector. In this project we used Histogram of Gradient (HOG) descriptor and SVM classifier for feature detection. We also show the relevance feedback can be applied to our localization and ranking algorithm. It gives high performance and accuracy. As a result, the presented system is more applicable to real-world problems than any prior contentbased video retrieval. It can be used for surveillance actions and also in many restricted areas for recognizing human actions.

EXISTING METHOD

In existing method a video surveillance system in the environment of a stationary camera that can extract moving targets from a video stream in real time and classify them into predefined categories according to their spatiotemporal properties. Targets are detected by computing the pixel-wise difference between consecutive frames, and then classified with a temporally boosted classifier and “spatiotemporal-oriented energy” analysis. The proposed classifier can successfully recognize five types of objects: a person, a bicycle, a motorcycle, a vehicle, and a person with an umbrella. In addition, we process targets that do not match any of the AdaBoost-based classifier’s categories by using a secondary classification module that categorizes such targets as crowds of individuals or noncrowds. We show that the above classification task can be performed effectively by analyzing a target’s spatiotemporal-oriented energies, which provide a rich description of the target’s spatial and dynamic features.

Moving target recognition involves two major steps: feature extraction and classification. The feature extraction process derives a set of features from the video stream. The second step analyzes the extracted features in order to make an appropriate classification decision. A variety of machine learning classification techniques have been investigated for surveillance tasks, e.g., support vector machines naïve Bayes classification and AdaBoost .

People are usually the main objects of interest in surveillance tasks. AdaBoost-based classifier is very effective at identifying individuals, but it is difficult to design and train it to recognize groups or crowds of people due to their
different shapes. In this work, define a “crowd” as two or more people in a small 11 spatial region. Although crowd (group) recognition has received some attention in recent years, most research that has focused on determining the number of people in a small spatial region has been cast within the people counting and tracking paradigms. Since occlusion and projective effects are two of the major challenges associated with crowd detection, many existing systems use 3-D positions of humans and require camera calibration. Human trackers that do not require camera
models have also been proposed.

Information to detect crowds without employing explicit tracking techniques. One notable exception is the approach in which uses space-time slices to detect crowds in urban road environments. As with AdaBoost-based classifier, the use of temporal information can greatly improve the performance of crowd detection systems. However, to avoid the complex tracking process and the detection and segmentation tasks that are often involved, analyze spatiotemporaloriented energies because they encapsulate spatial and dynamic information and do not require specific motion computations.

The framework that can detect and classify moving targets in video streams based on the targets’ spatiotemporal properties. Targets are detected by computing the pixel-wise difference between consecutive frames, and then classified with a temporally boosted classifier and “spatiotemporal- oriented energy” analysis. The classifier improves weak classifiers by allowing them to make use of previous information when evaluating a frame. In addition, a method for processing targets that do not match any of the AdaBoost-based classifier’s categories. Such targets are categorized as crowds of individuals or non-crowds. It is shown that moving crowd recognition can be performed effectively by using spatiotemporal-oriented energies. The proposed framework was tested on an extensive dataset. The detection rates demonstrate that the proposed system is extremely effective at recognizing all the predefined object classes.

HISTOGRAM OF GRADIENTS (HOG) DESCRIPTOR

Histogram of oriented gradients is a feature descriptor used to detect objects in computer vision and image processing. The HOG descriptor technique counts occurrences of gradient orientation in localized portions of an image – detection window or region of interest.

Implementation of the HOG descriptor algorithm is as follows:

  1. Divide the image into small connected regions called cells and for each cell compute a histogram of gradient directions or edge orientations for the pixels within the cell.
  2. Discretize each cell into angular bins according to the gradient orientation.
  3. Each cell’s pixel contributes weighted gradient to its corresponding angular bin.
  4. Group of adjacent cells are considered as spatial regions called blocks. The grouping of cells into a block is the basis for grouping and normalization of histogram.
  5. Normalized group of histograms represents the block histogram. The set of these block histogram represent the descriptor.

RESULT AND CONCLUSION

We first prepared each dataset for the retrieval experiments. The datasets were scaled uniformly to 240 pixels in height (maintaining aspect ratio) and 15 frames per second, so the feature extraction procedure was identical for both. We extracted features from each dataset at an average rate of 180 features per second, detecting features with multiscale Dollar and describing them with HOG3-D. The resulting features were clustered into 1000 code words after PCA was performed to capture 95% of the features’ variance. Time-slice histograms were generated over the whole dataset in batch before the main retrieval experiments; as these preprocessing steps can be performed before a retrieval search is performed, they are not included in the performance statistics. Each time slice was 10 frames in length, and the 2-D spatial grid was divided into 10 by 10 pixel blocks. These parameters were chosen based on observations of the minimum length and size of the actions within the dataset.

Electronics Engineering mini Projects

Video Frame

ADVANTAGES:

• High performance and accuracy.
• Time consumption.

APPLICATIONS:

• Used in surveillance actions.
• It can be used in CC TV action in banks, home security systems and also in colleges schools.

CONCLUSION:

Efficient content-based search systems, such as the model presented here, are becoming increasingly relevant in today’s . Effect on the accuracy of various spatial localization methods, as well as temporal localization alone. UT. UT Query Time Costs world, as sophisticated searches are increasingly necessary to navigate the huge amounts of data.
Through theoretical discussion and experimental results, we have demonstrated basic practical applicability of our system to this task of real-world video search. In designing our algorithm, we have taken an efficiency-first approach this has resulted in the creation of a fast permissive temporal-then-spatial localization technique, followed by a more orthodox histogram ranking step, both of which can be assisted by relevance feedback.

Credits:

ANNIE GEORGE
P.ELILARASI
P. JAYACHITRA

Tags: , , , , , , , , , , ,

Electronics Projects on AN EFFICIENT DLMS ADAPTIVE FIR IMPLEMENATION FOR EEG

June 12th, 2015 by admin | No Comments | Filed in 1000 Projects, ELECTRONICS PROJECTS, ENGINEERING PROJECTS

PROJECT ABSTRACT

This project presents an implementation of delayed mean square adaptive filter (DLMS) for the application of EEG. The noised EEG signals are filtered to obtain a clean EEG with the help of reference signal.By using delayed mean square adaptive filter (DLMS) the critical path and its architecture for fast and low-complexity implementation is also analyzed.The proposed structure of transpose form of DLMS adaptive filter provide much faster convergence and lower register complexity when compared to existing structure of direct form LMS adaptive filter.Based on the experimental results of proposed structure it is clear that one adaption delay method is best one for low area complexity.one of the structure of DLMS adaptive filter,one adaption delay method is used in application of EEG to obtain clean EEG signal. One adaption delay is 44% less in area and 29% less in delay when compared to zero adaption delay and it is 66% less in area and 22% less in delay when compared to two adaption delay.The proposed transpose form of DLMS adaptive filter are implemented for filtering the EEG signal by using Verilog HDL. These designs are simulated by using Modelsim 6.4c and Synthesized by Xilinx 9.1 to implement it in Spartan 3E FPGA Kit.

EXISTING SYSTEM

The least mean squares (LMS) algorithm adjust the filter coefficients to minimize the cost function.The LMS algorithms do not involve any matrix operations. Therefore, the LMS algorithms require fewer computational resources and memory. The eigen value spread of the input correlation matrix, or the correlation matrix of the input signal, might affect the convergence speed  of the resulting adaptive filter.

There are six different types of LMS algorithm they are Standard LMS, Normalized LMS, Leaky LMS, Normalized Leaky LMS, Sign LMS, Fast Block LMS. Among six fast block LMS is best one because the fast block LMS algorithm uses the fast Fourier transform (FFT) to transform the input signal x(n) to the frequency domain. This algorithm also updates the filter coefficients in the frequency domain. Updating the filter coefficients in the frequency domain can save computational resources.

Electronics engineering Projects

Fig Block diagram of fast block LMS

These are the following steps to calculate the output and error signals by using fast block LMS algorithm.

  1. Concatenates the current input signal block to the previous blocks.
  2. Performs an FFT to transform the input signal blocks from the time domain to the frequency domain.
  3. Multiplies the input signal blocks by the filter coefficients vector .
  4. Performs an inverse FFT (IFFT) on the multiplication result.
  5. Retrieves the last block from the result as the output signal vector .
  6. Calculates the error signal vector by comparing the input signal vector  with .

APPLICATIONS

A few popular applications for FIR filters are listed below:

  • Echo cancellation
  • Telecommunications
  • Data communications
  • Wireless communications
  • Video processing
  • Speech synthesis
  • Filtering
  • High-speed modems

CONCLUSION                                   

Based on a precise critical-path analysis, we have derived low-complexity architectures for the LMS adaptive filter. We have shown that the direct-form and transpose-form LMS adaptive filters have nearly the same critical-path delay. The direct-from LMS adaptive filter, however, involves less register complexity and provides much faster convergence than its transpose-form counterpart since the latter inherently performs delayed weight adaptation. We have proposed three different structures of direct-form LMS adaptive filter with i) zero adaptation delay ii) one adaptation delay and iii) two adaptation delays. Proposed Design 1 does not involve any adaptation delay. It has the minimum of MUF among all the structures, but that is adequate to support the highest data rate in current communication systems. Among all the three Design 2 is considered to be better. Finally the LMS Adaptive FIR Filter is implemented using Verilog language and dumped into FPGA Spartan Series Device.

 SCOPE WORK

We can modify the proposed system by further reducing the area and delay of the design in future by implementing it in digital receiver. We can also use this for other filtering applications.

SNAPSHOTS

ZERO ADAPTION DELAY FIR FILTER

Electronics Projects

Snapshot :Zero adaptation delay FIR filter

 

Credits:

K.BOOBHARATHI

K.JANANI

C.JERMINA

Tags: , , , , , , , , , ,

RAILWAY TRACK TRACER

October 2nd, 2011 by admin | 21 Comments | Filed in ELECTRICAL PROJECTS, ELECTRONICS PROJECTS

INTRODUCTION

In history of railways , almost 90% of the accidents happens because of two reasons:

  • Train comes away from track
  • Track discontinuity

TRAIN COMES AWAY FROM TRACK

It means that track is not all problems but train moves out of track. This happens because Of lack of concentration of the people who works with track.  For example when the nuts and bolts get loosed these sorts of problems will occur, where property loss will happen to both public and railways but not that much as the second case.  

TRACK DISCONTINUITY

i) This happens because of terrorism attack, natural disaster. There will be damage to track which causes severe damage to both public and railways which in many cases have led to several deaths.

ü) By keeping such issues in mind, we have come up with an idea to detect the track discontinuity very sooner before the train reaches the accident zone.

OBJECTIVE

Our project “railway track tracer” automatically traces the track discontinuity several kilometers ahead and alarms near by station and the Train about the track discontinuity.

ABSTRACT

  • In our project, we use series of sensors which senses the continuity of the track by sensing the vibration in the track.
  •  When a train passes its vibration in track it travels with very great velocity than the train velocity so that it can be detected several kilometers ahead before the train.

METHODOLOGY

Overview

In our project we use a series of sensors which detect the vibrations from the track. The output of the sensors are fed to the switching and rectifying circuit which processes the sensed signal ready to feed for the microcontroller. The processed signals are first fed to the opto couplers, output of which is fed to the microcontroller. The microcontroller decides from the received signal about the track discontinuity, and when a discontinuity is found in the track.

Block diagram for Railway track tracer

Block 1: Series of Sensors

We place the sensors at regular intervals in the track which senses the vibrations in the track when a train arrives. When a train moves with greater velocity the vibrations are experienced in the track for few kilometers ahead. The sensors capture these vibrations and pass them for processing.

Block 2: Switching and the Rectifying circuit

Every single sensor output is fed to a switching and rectifying circuit to determine the strength of vibration from the sensor and to process it to be suitable for the next level. Every switching circuit and the sensor pair is considered as a set (S1, S2, S3 and so on). Every set is connected to the microcontroller with suitable processing.

(more…)

Tags: , , , , , , , , , , ,

TOUCH ME NOT – For Playing Games-ECE Project

October 2nd, 2011 by admin | No Comments | Filed in ELECTRICAL PROJECTS, ELECTRONICS PROJECTS

ABSTRACT

Everyone likes to enjoy their free time in a more effective way. It would be more interesting and joyful if we spend the time in playing games, solving puzzles etc. Touch me not is an interesting project that allows the user to upgrade his concentration and a relief providing game.

This project is mainly designed as Events to be conducted at Exhibitions, Fetes etc. This project seems to be easy but it includes different interfacings with the microcontroller. This project uses 89C51 microcontroller. Seven segment displays are provided in this project for the display of various parameters like chances, time etc.

In this project, the user will be provided with a maximum of five chances and a time limit up to 180 seconds to play the game. The operator sets the chances and time using switches. LEDs are used in this project to indicate the number of chances selected.

Three switches are used to set the chances, time and start the game. Seven segment displays are used to display the numbers i.e., chances, entered time and current time. Once the chances and time are set, the operator presses the enter switch to start the game. Once the game is started, the time starts decreasing and the user has to play the game within the given time. The game is to move the iron rod from one end of the rope to the other end without touching the rope. If the rod touches the rope, the chances will be decremented by one and the game continues until the time is completed or the chances are equal to zero.

TOUCH ME NOT-BLOCK DIAGRAM

After the game is completed, the operator can press the enter switch once again for the next participant to play the game with the same settings i.e.; time and chance values set previously or can press the reset switch to start with the new settings.

(more…)

Tags: , , , , , , , , , , ,