add models and documents for vehicle and pedestrian detection (#3559)

* add modes and documents for vehicle and pedestrian detection

* remove needless output images

* add class names

* add Configure for training

* fix table in READ.md

* compress the images in the demo/output

* change the score_threshold for vehicle inference

* change Yolo v3 to YOLOv3

contrib/PedestrianDetection/pedestrian.json

+{
+    "images": [],
+    "annotations": [],
+    "categories": [
+        {
+            "supercategory": "component",
+            "id": 1,
+            "name": "pedestrian"
+        }
+   ]
+}

contrib/PedestrianDetection/pedestrian_yolov3_darknet.yml

+architecture: YOLOv3
+train_feed: YoloTrainFeed
+eval_feed: YoloEvalFeed
+test_feed: YoloTestFeed
+use_gpu: true
+max_iters: 200000
+log_smooth_window: 20
+save_dir: output
+snapshot_iter: 5000
+metric: COCO
+pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/DarkNet53_pretrained.tar
+weights: https://paddlemodels.bj.bcebos.com/object_detection/pedestrian_yolov3_darknet.tar
+num_classes: 1
+
+YOLOv3:
+  backbone: DarkNet
+  yolo_head: YOLOv3Head
+
+DarkNet:
+  norm_type: sync_bn
+  norm_decay: 0.
+  depth: 53
+
+YOLOv3Head:
+  anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]]
+  anchors: [[10, 13], [16, 30], [33, 23],
+            [30, 61], [62, 45], [59, 119],
+            [116, 90], [156, 198], [373, 326]]
+  norm_decay: 0.
+  ignore_thresh: 0.7
+  label_smooth: true
+  nms:
+    background_label: -1
+    keep_top_k: 100
+    nms_threshold: 0.45
+    nms_top_k: 1000
+    normalized: false
+    score_threshold: 0.01
+
+LearningRate:
+  base_lr: 0.001
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones:
+    - 150000
+    - 180000
+  - !LinearWarmup
+    start_factor: 0.
+    steps: 4000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2
+
+YoloTrainFeed:
+  batch_size: 8
+  dataset:
+    dataset_dir: dataset/pedestrian
+    annotation: annotations/instances_train2017.json
+    image_dir: train2017
+  num_workers: 8
+  bufsize: 128
+  use_process: true
+
+YoloEvalFeed:
+  batch_size: 8
+  image_shape: [3, 608, 608]
+  dataset:
+    dataset_dir: dataset/pedestrian
+    annotation: annotations/instances_val2017.json
+    image_dir: val2017
+
+YoloTestFeed:
+  batch_size: 1
+  image_shape: [3, 608, 608]
+  dataset:
+    annotation: contrib/PedestrianDetection/pedestrian.json

contrib/README.md

+# PaddleDetection applied for specific scenarios
+
+We provide some models implemented by PaddlePaddle to detect objects in specific scenarios, users can download the models and use them in these scenarios.
+
+| Task                 | Algorithm | Box AP | Download                                                                                |
+|:---------------------|:---------:|:------:| :-------------------------------------------------------------------------------------: |
+| Vehicle Detection    |  YOLOv3  |  54.5  | [model](https://paddlemodels.bj.bcebos.com/object_detection/vehicle_yolov3_darknet.tar) |
+| Pedestrian Detection |  YOLOv3  |  51.8  | [model](https://paddlemodels.bj.bcebos.com/object_detection/pedestrian_yolov3_darknet.tar) |
+
+## Vehicle Detection
+
+One of major applications of vehichle detection is traffic monitoring. In this scenary, vehicles to be detected are mostly captured by the cameras mounted on top of traffic light columns.
+
+### 1. Network
+
+The network for detecting vehicles is YOLOv3, the backbone of which is Dacknet53.
+
+### 2. Configuration for training
+
+PaddleDetection provides users with a configuration file [yolov3_darnet.yml](https://github.com/PaddlePaddle/models/blob/develop/PaddleCV/PaddleDetection/configs/yolov3_darknet.yml) to train YOLOv3 on the COCO dataset, compared with this file, we modify some parameters as followed to conduct the training for vehicle detection:
+
+* max_iters: 120000
+* num_classes: 6
+* anchors: [[8, 9], [10, 23], [19, 15], [23, 33], [40, 25], [54, 50], [101, 80], [139, 145], [253, 224]]
+* label_smooth: false
+* nms/nms_top_k: 400
+* nms/score_threshold: 0.005
+* milestones: [60000, 80000]
+* dataset_dir: dataset/vehicle
+
+### 3. Accuracy
+
+The accuracy of the model trained and evaluated on our private data is shown as followed:
+
+AP at IoU=.50:.05:.95 is 0.545.
+
+AP at IoU=.50 is 0.764.
+
+### 4. Inference
+
+Users can employ the model to conduct the inference:
+
+```
+export CUDA_VISIBLE_DEVICES=0
+export PYTHONPATH=$PYTHONPATH:.
+python -u tools/infer.py -c contrib/VehicleDetection/vehicle_yolov3_darknet.yml \
+                         -o weights=https://paddlemodels.bj.bcebos.com/object_detection/vehicle_yolov3_darknet.tar \ 
+                         --infer_dir contrib/VehicleDetection/demo \
+                         --draw_threshold 0.2 \
+                         --output_dir contrib/VehicleDetection/demo/output
+
+```
+
+Some inference results are visualized below:
+
+![](VehicleDetection/demo/output/001.jpeg)
+
+![](VehicleDetection/demo/output/005.png)
+
+## Pedestrian Detection
+
+The main applications of pedetestrian detection include intelligent monitoring. In this scenary, photos of pedetestrians are taken by surveillance cameras in public areas, then pedestrian detection are conducted on these photos.
+
+### 1. Network
+
+The network for detecting vehicles is YOLOv3, the backbone of which is Dacknet53.
+
+### 2. Configuration for training
+
+PaddleDetection provides users with a configuration file [yolov3_darnet.yml](https://github.com/PaddlePaddle/models/blob/develop/PaddleCV/PaddleDetection/configs/yolov3_darknet.yml) to train YOLOv3 on the COCO dataset, compared with this file, we modify some parameters as followed to conduct the training for pedestrian detection:
+
+* max_iters: 200000
+* num_classes: 1
+* snapshot_iter: 5000
+* milestones: [150000, 180000]
+* dataset_dir: dataset/pedestrian
+
+### 3. Accuracy
+
+The accuracy of the model trained and evaluted on our private data is shown as followed:
+
+AP at IoU=.50:.05:.95 is 0.518.
+
+AP at IoU=.50 is 0.792.
+
+### 4. Inference
+
+Users can employ the model to conduct the inference:
+
+```
+export CUDA_VISIBLE_DEVICES=0
+export PYTHONPATH=$PYTHONPATH:.
+python -u tools/infer.py -c contrib/PedestrianDetection/pedestrian_yolov3_darknet.yml \ 
+                         -o weights=https://paddlemodels.bj.bcebos.com/object_detection/pedestrian_yolov3_darknet.tar \
+                         --infer_dir contrib/PedestrianDetection/demo \ 
+                         --draw_threshold 0.3 \
+                         --output_dir contrib/PedestrianDetection/demo/output
+```
+
+Some inference results are visualized below:
+
+![](PedestrianDetection/demo/output/001.png)
+
+![](PedestrianDetection/demo/output/004.png)

contrib/README_cn.md

+# PaddleDetection 特色垂类检测模型
+
+我们提供了针对不同场景的基于PaddlePaddle的检测模型，用户可以下载模型进行使用。
+
+| 任务                 | 算法 | 精度(Box AP) | 下载                                                                                |
+|:---------------------|:---------:|:------:| :---------------------------------------------------------------------------------: |
+| 车辆检测    |  YOLOv3  |  54.5  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/vehicle_yolov3_darknet.tar) |
+| 行人检测 |  YOLOv3  |  51.8  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/pedestrian_yolov3_darknet.tar) |
+
+
+## 车辆检测（Vehicle Detection）
+
+车辆检测的主要应用之一是交通监控。在这样的监控场景中，待检测的车辆多为道路红绿灯柱上的摄像头拍摄所得。
+
+### 1. 模型结构
+
+Backbone为Dacknet53的YOLOv3。
+
+### 2. 训练参数配置
+
+PaddleDetection提供了使用COCO数据集对YOLOv3进行训练的参数配置文件[yolov3_darnet.yml](https://github.com/PaddlePaddle/models/blob/develop/PaddleCV/PaddleDetection/configs/yolov3_darknet.yml)，与之相比，在进行车辆检测的模型训练时，我们对以下参数进行了修改：
+
+* max_iters: 120000
+* num_classes: 6
+* anchors: [[8, 9], [10, 23], [19, 15], [23, 33], [40, 25], [54, 50], [101, 80], [139, 145], [253, 224]]
+* label_smooth: false
+* nms/nms_top_k: 400
+* nms/score_threshold: 0.005
+* milestones: [60000, 80000]
+* dataset_dir: dataset/vehicle
+
+### 3. 精度指标
+
+模型在我们内部数据上的精度指标为：
+
+IOU=.50:.05:.95时的AP为 0.545。
+
+IOU=.5时的AP为 0.764。
+
+### 4. 预测
+
+用户可以使用我们训练好的模型进行车辆检测：
+
+```
+export CUDA_VISIBLE_DEVICES=0
+export PYTHONPATH=$PYTHONPATH:.
+python -u tools/infer.py -c contrib/VehicleDetection/vehicle_yolov3_darknet.yml \
+                         -o weights=https://paddlemodels.bj.bcebos.com/object_detection/vehicle_yolov3_darknet.tar \ 
+                         --infer_dir contrib/VehicleDetection/demo \
+                         --draw_threshold 0.2 \
+                         --output_dir contrib/VehicleDetection/demo/output
+
+```
+
+预测结果示例：
+
+![](VehicleDetection/demo/output/001.jpeg)
+
+![](VehicleDetection/demo/output/005.png)
+
+## 行人检测（Pedestrian Detection）
+
+行人检测的主要应用有智能监控。在监控场景中，大多是从公共区域的监控摄像头视角拍摄行人，获取图像后再进行行人检测。
+
+### 1. 模型结构
+
+Backbone为Dacknet53的YOLOv3。
+
+
+### 2. 训练参数配置
+
+PaddleDetection提供了使用COCO数据集对YOLOv3进行训练的参数配置文件[yolov3_darnet.yml](https://github.com/PaddlePaddle/models/blob/develop/PaddleCV/PaddleDetection/configs/yolov3_darknet.yml)，与之相比，在进行行人检测的模型训练时，我们对以下参数进行了修改：
+
+* max_iters: 200000
+* num_classes: 1
+* snapshot_iter: 5000
+* milestones: [150000, 180000]
+* dataset_dir: dataset/pedestrian
+
+### 2. 精度指标
+
+模型在我们针对监控场景的内部数据上精度指标为：
+
+IOU=.5时的AP为 0.792。
+
+IOU=.5-.95时的AP为 0.518。
+
+### 3. 预测
+
+用户可以使用我们训练好的模型进行行人检测：
+
+```
+export CUDA_VISIBLE_DEVICES=0
+export PYTHONPATH=$PYTHONPATH:.
+python -u tools/infer.py -c contrib/PedestrianDetection/pedestrian_yolov3_darknet.yml \ 
+                         -o weights=https://paddlemodels.bj.bcebos.com/object_detection/pedestrian_yolov3_darknet.tar \
+                         --infer_dir contrib/PedestrianDetection/demo \ 
+                         --draw_threshold 0.3 \
+                         --output_dir contrib/PedestrianDetection/demo/output
+```
+
+预测结果示例：
+
+![](PedestrianDetection/demo/output/001.png)
+
+![](PedestrianDetection/demo/output/004.png)

contrib/VehicleDetection/vehicle.json

+{
+    "images": [],
+    "annotations": [],
+    "categories": [
+        {
+            "supercategory": "component",
+            "id": 1,
+            "name": "car"
+        },
+        {
+            "supercategory": "component",
+            "id": 2,
+            "name": "truck"
+        },
+        {
+            "supercategory": "component",
+            "id": 3,
+            "name": "bus"
+        },
+        {
+            "supercategory": "component",
+            "id": 4,
+            "name": "motorbike"
+        },
+        {
+            "supercategory": "component",
+            "id": 5,
+            "name": "tricycle"
+        },
+        {
+            "supercategory": "component",
+            "id": 6,
+            "name": "carplate"
+        }
+    ]
+}

contrib/VehicleDetection/vehicle_yolov3_darknet.yml

+architecture: YOLOv3
+train_feed: YoloTrainFeed
+eval_feed: YoloEvalFeed
+test_feed: YoloTestFeed
+use_gpu: true
+max_iters: 120000
+log_smooth_window: 20
+save_dir: output
+snapshot_iter: 2000
+metric: COCO
+pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/DarkNet53_pretrained.tar
+weights: https://paddlemodels.bj.bcebos.com/object_detection/vehicle_yolov3_darknet.tar
+num_classes: 6
+
+YOLOv3:
+  backbone: DarkNet
+  yolo_head: YOLOv3Head
+
+DarkNet:
+  norm_type: sync_bn
+  norm_decay: 0.
+  depth: 53
+
+YOLOv3Head:
+  anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]]
+  anchors: [[8, 9], [10, 23], [19, 15],
+            [23, 33], [40, 25], [54, 50],
+            [101, 80], [139, 145], [253, 224]]
+  norm_decay: 0.
+  ignore_thresh: 0.7
+  label_smooth: false
+  nms:
+    background_label: -1
+    keep_top_k: 100
+    nms_threshold: 0.45
+    nms_top_k: 400
+    normalized: false
+    score_threshold: 0.005
+
+LearningRate:
+  base_lr: 0.001
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones:
+    - 60000
+    - 80000
+  - !LinearWarmup
+    start_factor: 0.
+    steps: 4000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2
+
+YoloTrainFeed:
+  batch_size: 8
+  dataset:
+    dataset_dir: dataset/vehicle
+    annotation: annotations/instances_train2017.json
+    image_dir: train2017
+  num_workers: 8
+  bufsize: 128
+  use_process: true
+
+YoloEvalFeed:
+  batch_size: 8
+  image_shape: [3, 608, 608]
+  dataset:
+    dataset_dir: dataset/vehicle
+    annotation: annotations/instances_val2017.json
+    image_dir: val2017
+
+YoloTestFeed:
+  batch_size: 1
+  image_shape: [3, 608, 608]
+  dataset:
+    annotation: contrib/VehicleDetection/vehicle.json