最详细的目标检测SSD算法讲解
深度学习之目标检测 SSD的理解和细节分析
SSD算法—-模型结构的详解及Python源码分析
SSD框架详细解读（一）

关于SSD的实现，参考了https://github.com/balancap/SDC-Vehicle-Detection，其中阐述了实现的细节。
the SSD network used the concept of anchor boxes for object detection. The image below illustrates the concept: at several scales are pre-defined boxes with different sizes and ratios. The goal of SSD convolutional network is, for each of these anchor boxes, to detect if there is an object inside this box (or closely), and compute the offset between the object bounding box and the fixed anchor box.

In the case of SSD network, we use VGG16 as a based architecture: it provides high quality features at different scales, the former being then used as inputs for multibox modules in charge of computing the object type and coordinates for each anchor boxes. The architecture of the network we use is illustrated in the following TensorBoard graph. It follows the original SSD paper:

Convolutional Blocks 1 to 7 are exactly VGG modules. Hence, these weights can be imported from VGG weights, speeding massively training time;
Blocks 8 to 11 are additional feature blocks. They consist of two convolutional layers each: a 3x3 convolution followed by a 1x1 convolution;
Yellow blocks are multibox modules: they take VGG-type features as inputs, and outputs two components: a softmax Tensor which gives for every anchor box the probability of an object being detected, and an offset Tensor which describes the offset between the object bounding box and the anchor box. These two Tensors are the results of two different 3x3 convolutions of the input Tensor.

For instance, consider the 8x8 feature block described in the image above. At every coordinate in the grid, it defines 4 anchor boxes of different dimensions. The multibox module taking this feature Tensor as input will thus provide two output Tensors: a classification Tensor of shape 8x8x4xNClasses and an offset Tensor of shape 8x8x4x4, where in the latter, the last dimension stands for the 4 coordinates of every bounding box.

As a result, the global SSD network will provide a classification score and an offset for a total of 8732 anchor boxes. During training, we therefore try to minimize both errors: the classification error on every anchor box and the localization error when there is a positive match with a grountruth bounding box. We refer to the original SSD paper for the precise equations defining the loss function.

SSD模型结构与YOLO对比

完整的模型图请点击：
https://github.com/bjzhao143/objectiveDetect/blob/master/models/ssd300_model.png

anchors计算示意图

预训练的SSD-tesnforflow模型

本人下载了https://github.com/HiKapok/SSD.TensorFlow中的代码和预训练模型，用于细粒度识别。

附录：VGG16与VGG19的模块

首先解释一下图中的结构，ABCDE分别为当时VGG项目组测试的不同的网络结构，对于不同的结构进行了效果上的比较，从中发现LRN（local response normalization）好像并没什么用，之后就在后面的结构中舍弃了。图中D和E分别为VGG16和VGG19。

VGG19中的“19”是怎么来的？

在模型文件中，VGG19把激活层也当作一层，因此具有43个layers：

#43 layers
VGG19_LAYERS = ('conv1_1', 'relu1_1', 'conv1_2', 'relu1_2', 'pool1','conv2_1', 'relu2_1', 'conv2_2', 'relu2_2', 'pool2','conv3_1', 'relu3_1', 'conv3_2', 'relu3_2', 'conv3_3', 'relu3_3', 'conv3_4', 'relu3_4', 'pool3','conv4_1', 'relu4_1', 'conv4_2', 'relu4_2', 'conv4_3', 'relu4_3', 'conv4_4', 'relu4_4', 'pool4','conv5_1', 'relu5_1', 'conv5_2', 'relu5_2', 'conv5_3', 'relu5_3', 'conv5_4', 'relu5_4', 'pool5','fc6', 'relu6','fc7', 'relu7','fc8', 'softmax',)

神经网络实现---SSD相关推荐

ssd训练自己数据集
1.用labelImg标数据 2.将数据转换为tfrecord 错误记录: NotFoundError:无法创建NewWriteableFile 解决方法:您需要在运行此脚本的运行环境文件夹中自己创建 ...
（一）目标检测定位算法之SSD检测自己的图片
参考 https://blog.csdn.net/zzz_cming/article/details/81128460 1.下载SSD-Tensorflow https://download.cs ...
Opencv C++ 学习视频整理源代码（1）
0.代码基本框架 #include <opencv2/opencv.hpp> #include <opencv2/tracking.hpp> #include <iost ...
pytorch系统学习
经过网络后的输出图片形状的计算公式: 第一种情况:如果stride值为0的话,输入形状是n_h x n_w,卷积核窗口是k_h x k_w,那么输出形状是(n_h - k_h +1) x (n_w - ...
基于CNN目标检测方法（RCNN，Fast-RCNN，Faster-RCNN，Mask-RCNN，YOLO，SSD）行人检测，目标追踪，卷积神经网络
一.研究意义卷积神经网络(CNN)由于其强大的特征提取能力,近年来被广泛用于计算机视觉领域.1998年Yann LeCun等提出的LeNet-5网络结构,该结构使得卷积神经网络可以端到端的训练,并应 ...
matlab ssd检测,基于SSD神经网络的违章停车车辆实时检测方法与流程
本发明属于图像识别和计算机视觉技术领域,尤其涉及一种停车车辆的检测方法,可用于城市环境中对违章停车车辆的检测. 背景技术: 随着现代社会经济的快速发展和城市化的普及,汽车作为一种重要的交通工具,其数量 ...
OpenCv-C++-深度神经网络（DNN）模块-使用SSD模型实现对象检测
首先我们要搞明白图像分类和对象检测的区别: 1.图像分类: 图像分类就是将这幅图像归为某一类,图像中的对象尽量要单一. 2.对象检测: 对象检测就是将不同的对象用框圈出来并规定为某一类,对象可以多个. ...
基于神经网络的目标检测论文之目标检测方法：改进的SSD目标检测算法
4.2 改进的SSD 上一章我们了解到,物体识别检测算法是在传统CNN算法基础上加上目标区域建议策略和边框回归算法得到的.前辈们的工作主要体现在目标区域建议的改进策略上,从最开始的穷举建议框,到划分图 ...
神经网络: SSD目标检测网络解析
一.SSD(Single Shot MultiBox Detector)简介 SSD是2016年ICCV的一篇论文,是目前为止主要的目标检测算法. 算法的主要优点: 速度比Faster-Rcnn快,精 ...

神经网络实现---SSD

SSD模型结构与YOLO对比

anchors计算示意图

预训练的SSD-tesnforflow模型

附录：VGG16与VGG19的模块

神经网络实现---SSD相关推荐

最新文章

热门文章