A combined HOG and deep convolution network cascade for pedestrian detection

Lipetski, Yuriy; Sidla, Oliver

doi:10.2352/issn.2470-1173.2017.4.srv-350

Cited by 4 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast to the traditional HOG-SVM approach, Convolutional Neural Networks (CNNs) have demonstrated their superiority in efficiently extracting high-level contour features and achieving state-ofthe-art performance in real-time multiple-object tracking (MOT) [29]. CNN-based models primarily focus on local feature extraction, often overlooking global features [30]. To address this limitation, a hybrid approach combining HOG and CNN has been proposed to enhance the performance of detection models.…”

Section: Literature Reviewmentioning

confidence: 99%

“…In 2016, Zhang et al utilized HOG to eliminate background noise when constructing detection models for moving objects in videos, resulting in excellent performance for detecting moving objects in applications such as food and agricultural traceability analysis [31]. Building upon this foundation, Lipetski et al introduced the HCNN model by integrating the HOG descriptor with CNN to enhance the quality of pedestrian detection [30]. Rui et al presented an algorithm that leverages various feature maps from the initial CNN layer as input to HOG, demonstrating that combining HOG-based multi-convolutional features for pedestrian detection can yield high accuracy and stable network performance [32].…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Effect of Positive-Negative Image Ratio on the Performance of Pedestrian Detection Model

Kok Yee,

Lit Ken,

Sim Choo

et al. 2024

Mal. J. Fund. Appl. Sci.

View full text Add to dashboard Cite

Pedestrian detection holds significant importance in computer vision, finding applications in video surveillance, human-computer interaction, and autonomous vehicles. Surprisingly, there is a scarcity of research addressing the optimal ratio of positive to negative images for training detection models. This study endeavors to fill this research gap by exploring various detection models and determining the ideal ratio. Two distinct scenarios are investigated, each characterized by an equal total image count and an equivalent number of positive images sourced from CVC-14 night/visible, night/FIR, and INRIA databases. The study leverages the Histogram of Oriented Gradient, utilizing both Support Vector Machines and Medium Neural Networks to construct the detection models. Notably, the experiments reveal that the accuracy of the models remains relatively stable, even with an increase in the ratio of negative images. However, a noteworthy inverse relationship between sensitivity and specificity emerges as the ratio escalates. The findings, guided by the Youden Index, pinpoint the optimal training ratio for pedestrian detection models, falling within the range of 1:0.5 to 1:2In the CVC-14 nighttime database, the Youden index reached 100% when the model was trained with a 1:0.5 ratio using SVM, and a total of 4500 images were employed in the training process. On the other hand, in the INRIA dataset, the Youden index exhibited its highest value at 98.50%. This occurred when both SVM and a Medium neural network were utilized to train the model with a ratio of 1:2, utilizing a total of 3000 images for the training phase. It's worth highlighting that the processing time for SVM models lags behind that of Medium Neural Networks. This disparity arises from the heightened computational complexity inherent to medium-sized neural networks, making them computationally demanding compared to SVMs. This study contributes valuable insights into the nuanced relationship between image ratios and the performance of pedestrian detection models.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Effect of Positive-Negative Image Ratio on the Performance of Pedestrian Detection Model

Kok Yee,

Lit Ken,

Sim Choo

et al. 2024

Mal. J. Fund. Appl. Sci.

View full text Add to dashboard Cite

show abstract

“…The technique merged the handcrafted features with a deep convolutional neural network (DCNN) and served as the concrete foundation to expand in the computer vision field. Then Lipetski et al [ 5 ] took advantage of the laid foundation and combined the HOG descriptor with CNN to form the HCNN model for improving the pedestrian detection quality rate. They extracted HOG features and fed them into the CNN as input to increase classification and detection rates.…”

Section: Related Workmentioning

confidence: 99%

“…Despite the state-of-the-art achievement, the traditional CNN proposed algorithms tend to ignore the global features [ 5 ]. Their detectors are mainly based on the local features extraction for the application to understand the image information [ 6 ].…”

Section: Introductionmentioning

confidence: 99%

Enhancing Detection Quality Rate with a Combined HOG and CNN for Real-Time Multiple Object Tracking across Non-Overlapping Multiple Cameras

Kalake

Dong

Wan

et al. 2022

Sensors

View full text Add to dashboard Cite

Multi-object tracking in video surveillance is subjected to illumination variation, blurring, motion, and similarity variations during the identification process in real-world practice. The previously proposed applications have difficulties in learning the appearances and differentiating the objects from sundry detections. They mostly rely heavily on local features and tend to lose vital global structured features such as contour features. This contributes to their inability to accurately detect, classify or distinguish the fooling images. In this paper, we propose a paradigm aimed at eliminating these tracking difficulties by enhancing the detection quality rate through the combination of a convolutional neural network (CNN) and a histogram of oriented gradient (HOG) descriptor. We trained the algorithm with an input of 120 × 32 images size and cleaned and converted them into binary for reducing the numbers of false positives. In testing, we eliminated the background on frames size and applied morphological operations and Laplacian of Gaussian model (LOG) mixture after blobs. The images further underwent feature extraction and computation with the HOG descriptor to simplify the structural information of the objects in the captured video images. We stored the appearance features in an array and passed them into the network (CNN) for further processing. We have applied and evaluated our algorithm for real-time multiple object tracking on various city streets using EPFL multi-camera pedestrian datasets. The experimental results illustrate that our proposed technique improves the detection rate and data associations. Our algorithm outperformed the online state-of-the-art approach by recording the highest in precisions and specificity rates.

show abstract

“…Convolutional Neural Networks (CNNs) have shown great potential due to their computational efficiency, and they are also capable of performing well on images [8]. Despite the state-of-the-art achievement, the traditional CNN proposed algorithms tend to ignore the global features [9]. They continue to suffer from identifying the shape and boundary characteristics from the captured images [10].…”

Section: Introductionmentioning

confidence: 99%

Emotion Recognition using a 4-layer Network

Goyal,

Wahale,

Agarwal

et al. 2024

Preprint

View full text Add to dashboard Cite

The emotional intelligence has emerged as an important area of research in artificial intelligence covering wide range of real-life domains. A significant contribution has also been made to bring new insights in the field of emotional intelligence and intelligent software agents. Learning agents and educational activities are very attractive for incorporation of emotional aspects in artificial intelligence. Emotions have an important role in intelligent behaviour and influence the human decision-making process. An overview of the state-of-the-art in emotional intelligence research with emphasis on emotional agents has been given covering the area like Emotion detection, Emotional agents, Text emotion detection, Modelling artificial agent’s environments, Emotional intelligence and different forms of learning, Emotional agents in robotics, Emotional intelligence in decision support processes, Emotional intelligence in interactive environments, Emotional intelligence in classification and search, Emotion models. Taking the first step, the following review discuss about our work on emotion detection.

show abstract

A combined HOG and deep convolution network cascade for pedestrian detection

Cited by 4 publications

References 0 publications

Effect of Positive-Negative Image Ratio on the Performance of Pedestrian Detection Model

Effect of Positive-Negative Image Ratio on the Performance of Pedestrian Detection Model

Enhancing Detection Quality Rate with a Combined HOG and CNN for Real-Time Multiple Object Tracking across Non-Overlapping Multiple Cameras

Emotion Recognition using a 4-layer Network

Contact Info

Product

Resources

About